Upload folder using huggingface_hub
Browse files- config.json +57 -0
- generation_config.json +10 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2072 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vision_tower/added_tokens.json +1026 -0
- vision_tower/config.json +237 -0
- vision_tower/configuration_florence2.py +340 -0
- vision_tower/merges.txt +0 -0
- vision_tower/modeling_florence2.py +0 -0
- vision_tower/preprocessor_config.json +33 -0
- vision_tower/processing_florence2.py +1124 -0
- vision_tower/processor_config.json +6 -0
- vision_tower/pytorch_model.bin +3 -0
- vision_tower/special_tokens_map.json +0 -0
- vision_tower/tokenizer.json +0 -0
- vision_tower/tokenizer_config.json +0 -0
- vision_tower/vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/fsx_0/user/jiuhai/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/4281e96c7cf5ab6b312ef0cb78373efa3976a9dd",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaLlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 128000,
|
9 |
+
"eos_token_id": [
|
10 |
+
128001,
|
11 |
+
128008,
|
12 |
+
128009
|
13 |
+
],
|
14 |
+
"freeze_mm_mlp_adapter": false,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 4096,
|
17 |
+
"image_aspect_ratio": "square",
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 14336,
|
20 |
+
"max_position_embeddings": 131072,
|
21 |
+
"mlp_bias": false,
|
22 |
+
"mm_hidden_size": 1024,
|
23 |
+
"mm_patch_merge_type": "flat",
|
24 |
+
"mm_projector_lr": null,
|
25 |
+
"mm_projector_type": "mlp3x_gelu",
|
26 |
+
"mm_use_im_patch_token": false,
|
27 |
+
"mm_use_im_start_end": false,
|
28 |
+
"mm_vision_select_feature": "patch",
|
29 |
+
"mm_vision_select_layer": -2,
|
30 |
+
"mm_vision_tower": "/fsx_0/user/jiuhai/hub/models--microsoft--Florence-2-large-ft/snapshots/c669c6b8bfbd7f0193fcb31f997879045a3612f3",
|
31 |
+
"model_type": "llava_llama",
|
32 |
+
"num_attention_heads": 32,
|
33 |
+
"num_hidden_layers": 32,
|
34 |
+
"num_key_value_heads": 8,
|
35 |
+
"pad_token_id": 128256,
|
36 |
+
"pretraining_tp": 1,
|
37 |
+
"rms_norm_eps": 1e-05,
|
38 |
+
"rope_scaling": {
|
39 |
+
"factor": 8.0,
|
40 |
+
"high_freq_factor": 4.0,
|
41 |
+
"low_freq_factor": 1.0,
|
42 |
+
"original_max_position_embeddings": 8192,
|
43 |
+
"rope_type": "llama3"
|
44 |
+
},
|
45 |
+
"rope_theta": 500000.0,
|
46 |
+
"tie_word_embeddings": false,
|
47 |
+
"tokenizer_model_max_length": 2048,
|
48 |
+
"tokenizer_padding_side": "right",
|
49 |
+
"torch_dtype": "bfloat16",
|
50 |
+
"transformers_version": "4.43.2",
|
51 |
+
"tune_entire_model": true,
|
52 |
+
"tune_mm_mlp_adapter": false,
|
53 |
+
"use_cache": true,
|
54 |
+
"use_mm_proj": true,
|
55 |
+
"vision_tower_lr": null,
|
56 |
+
"vocab_size": 128257
|
57 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128008,
|
7 |
+
128009
|
8 |
+
],
|
9 |
+
"transformers_version": "4.43.2"
|
10 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:983e4d4f4edadfc22a66cfadcb996098b9b3c9bb81d27ee62a2c3126bd088582
|
3 |
+
size 4976706864
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:161f9e106a170102fdb79b6b82a32ddcf57e6e74b89994aef7444f58cf97e4f8
|
3 |
+
size 4999802720
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e19c4cd91b75587ceb376c2369a0b7a2c4794b8f1fb60288c467be9eb75e7223
|
3 |
+
size 4915916176
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41fd9549a16bb5d531fc01df052f9f253326b2a19f278dd95b12a39189f99480
|
3 |
+
size 3124967970
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2072 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
},
|
2051 |
+
"128256": {
|
2052 |
+
"content": "<pad>",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": false,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": true
|
2058 |
+
}
|
2059 |
+
},
|
2060 |
+
"bos_token": "<|begin_of_text|>",
|
2061 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
2062 |
+
"clean_up_tokenization_spaces": true,
|
2063 |
+
"eos_token": "<|eot_id|>",
|
2064 |
+
"model_input_names": [
|
2065 |
+
"input_ids",
|
2066 |
+
"attention_mask"
|
2067 |
+
],
|
2068 |
+
"model_max_length": 2048,
|
2069 |
+
"pad_token": "<pad>",
|
2070 |
+
"padding_side": "right",
|
2071 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2072 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff057ddb6fe6177ab7589761ff2178a6a6a0d5eaac7c70c9c63d3f37fbb58c3e
|
3 |
+
size 6904
|
vision_tower/added_tokens.json
ADDED
@@ -0,0 +1,1026 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</cap>": 51270,
|
3 |
+
"</dcap>": 51274,
|
4 |
+
"</grounding>": 51276,
|
5 |
+
"</ncap>": 51272,
|
6 |
+
"</ocr>": 50268,
|
7 |
+
"</od>": 50266,
|
8 |
+
"</poly>": 51287,
|
9 |
+
"</proposal>": 51285,
|
10 |
+
"</region_cap>": 51281,
|
11 |
+
"</region_to_desciption>": 51283,
|
12 |
+
"</seg>": 51278,
|
13 |
+
"<and>": 51288,
|
14 |
+
"<cap>": 51269,
|
15 |
+
"<dcap>": 51273,
|
16 |
+
"<grounding>": 51275,
|
17 |
+
"<loc_0>": 50269,
|
18 |
+
"<loc_100>": 50369,
|
19 |
+
"<loc_101>": 50370,
|
20 |
+
"<loc_102>": 50371,
|
21 |
+
"<loc_103>": 50372,
|
22 |
+
"<loc_104>": 50373,
|
23 |
+
"<loc_105>": 50374,
|
24 |
+
"<loc_106>": 50375,
|
25 |
+
"<loc_107>": 50376,
|
26 |
+
"<loc_108>": 50377,
|
27 |
+
"<loc_109>": 50378,
|
28 |
+
"<loc_10>": 50279,
|
29 |
+
"<loc_110>": 50379,
|
30 |
+
"<loc_111>": 50380,
|
31 |
+
"<loc_112>": 50381,
|
32 |
+
"<loc_113>": 50382,
|
33 |
+
"<loc_114>": 50383,
|
34 |
+
"<loc_115>": 50384,
|
35 |
+
"<loc_116>": 50385,
|
36 |
+
"<loc_117>": 50386,
|
37 |
+
"<loc_118>": 50387,
|
38 |
+
"<loc_119>": 50388,
|
39 |
+
"<loc_11>": 50280,
|
40 |
+
"<loc_120>": 50389,
|
41 |
+
"<loc_121>": 50390,
|
42 |
+
"<loc_122>": 50391,
|
43 |
+
"<loc_123>": 50392,
|
44 |
+
"<loc_124>": 50393,
|
45 |
+
"<loc_125>": 50394,
|
46 |
+
"<loc_126>": 50395,
|
47 |
+
"<loc_127>": 50396,
|
48 |
+
"<loc_128>": 50397,
|
49 |
+
"<loc_129>": 50398,
|
50 |
+
"<loc_12>": 50281,
|
51 |
+
"<loc_130>": 50399,
|
52 |
+
"<loc_131>": 50400,
|
53 |
+
"<loc_132>": 50401,
|
54 |
+
"<loc_133>": 50402,
|
55 |
+
"<loc_134>": 50403,
|
56 |
+
"<loc_135>": 50404,
|
57 |
+
"<loc_136>": 50405,
|
58 |
+
"<loc_137>": 50406,
|
59 |
+
"<loc_138>": 50407,
|
60 |
+
"<loc_139>": 50408,
|
61 |
+
"<loc_13>": 50282,
|
62 |
+
"<loc_140>": 50409,
|
63 |
+
"<loc_141>": 50410,
|
64 |
+
"<loc_142>": 50411,
|
65 |
+
"<loc_143>": 50412,
|
66 |
+
"<loc_144>": 50413,
|
67 |
+
"<loc_145>": 50414,
|
68 |
+
"<loc_146>": 50415,
|
69 |
+
"<loc_147>": 50416,
|
70 |
+
"<loc_148>": 50417,
|
71 |
+
"<loc_149>": 50418,
|
72 |
+
"<loc_14>": 50283,
|
73 |
+
"<loc_150>": 50419,
|
74 |
+
"<loc_151>": 50420,
|
75 |
+
"<loc_152>": 50421,
|
76 |
+
"<loc_153>": 50422,
|
77 |
+
"<loc_154>": 50423,
|
78 |
+
"<loc_155>": 50424,
|
79 |
+
"<loc_156>": 50425,
|
80 |
+
"<loc_157>": 50426,
|
81 |
+
"<loc_158>": 50427,
|
82 |
+
"<loc_159>": 50428,
|
83 |
+
"<loc_15>": 50284,
|
84 |
+
"<loc_160>": 50429,
|
85 |
+
"<loc_161>": 50430,
|
86 |
+
"<loc_162>": 50431,
|
87 |
+
"<loc_163>": 50432,
|
88 |
+
"<loc_164>": 50433,
|
89 |
+
"<loc_165>": 50434,
|
90 |
+
"<loc_166>": 50435,
|
91 |
+
"<loc_167>": 50436,
|
92 |
+
"<loc_168>": 50437,
|
93 |
+
"<loc_169>": 50438,
|
94 |
+
"<loc_16>": 50285,
|
95 |
+
"<loc_170>": 50439,
|
96 |
+
"<loc_171>": 50440,
|
97 |
+
"<loc_172>": 50441,
|
98 |
+
"<loc_173>": 50442,
|
99 |
+
"<loc_174>": 50443,
|
100 |
+
"<loc_175>": 50444,
|
101 |
+
"<loc_176>": 50445,
|
102 |
+
"<loc_177>": 50446,
|
103 |
+
"<loc_178>": 50447,
|
104 |
+
"<loc_179>": 50448,
|
105 |
+
"<loc_17>": 50286,
|
106 |
+
"<loc_180>": 50449,
|
107 |
+
"<loc_181>": 50450,
|
108 |
+
"<loc_182>": 50451,
|
109 |
+
"<loc_183>": 50452,
|
110 |
+
"<loc_184>": 50453,
|
111 |
+
"<loc_185>": 50454,
|
112 |
+
"<loc_186>": 50455,
|
113 |
+
"<loc_187>": 50456,
|
114 |
+
"<loc_188>": 50457,
|
115 |
+
"<loc_189>": 50458,
|
116 |
+
"<loc_18>": 50287,
|
117 |
+
"<loc_190>": 50459,
|
118 |
+
"<loc_191>": 50460,
|
119 |
+
"<loc_192>": 50461,
|
120 |
+
"<loc_193>": 50462,
|
121 |
+
"<loc_194>": 50463,
|
122 |
+
"<loc_195>": 50464,
|
123 |
+
"<loc_196>": 50465,
|
124 |
+
"<loc_197>": 50466,
|
125 |
+
"<loc_198>": 50467,
|
126 |
+
"<loc_199>": 50468,
|
127 |
+
"<loc_19>": 50288,
|
128 |
+
"<loc_1>": 50270,
|
129 |
+
"<loc_200>": 50469,
|
130 |
+
"<loc_201>": 50470,
|
131 |
+
"<loc_202>": 50471,
|
132 |
+
"<loc_203>": 50472,
|
133 |
+
"<loc_204>": 50473,
|
134 |
+
"<loc_205>": 50474,
|
135 |
+
"<loc_206>": 50475,
|
136 |
+
"<loc_207>": 50476,
|
137 |
+
"<loc_208>": 50477,
|
138 |
+
"<loc_209>": 50478,
|
139 |
+
"<loc_20>": 50289,
|
140 |
+
"<loc_210>": 50479,
|
141 |
+
"<loc_211>": 50480,
|
142 |
+
"<loc_212>": 50481,
|
143 |
+
"<loc_213>": 50482,
|
144 |
+
"<loc_214>": 50483,
|
145 |
+
"<loc_215>": 50484,
|
146 |
+
"<loc_216>": 50485,
|
147 |
+
"<loc_217>": 50486,
|
148 |
+
"<loc_218>": 50487,
|
149 |
+
"<loc_219>": 50488,
|
150 |
+
"<loc_21>": 50290,
|
151 |
+
"<loc_220>": 50489,
|
152 |
+
"<loc_221>": 50490,
|
153 |
+
"<loc_222>": 50491,
|
154 |
+
"<loc_223>": 50492,
|
155 |
+
"<loc_224>": 50493,
|
156 |
+
"<loc_225>": 50494,
|
157 |
+
"<loc_226>": 50495,
|
158 |
+
"<loc_227>": 50496,
|
159 |
+
"<loc_228>": 50497,
|
160 |
+
"<loc_229>": 50498,
|
161 |
+
"<loc_22>": 50291,
|
162 |
+
"<loc_230>": 50499,
|
163 |
+
"<loc_231>": 50500,
|
164 |
+
"<loc_232>": 50501,
|
165 |
+
"<loc_233>": 50502,
|
166 |
+
"<loc_234>": 50503,
|
167 |
+
"<loc_235>": 50504,
|
168 |
+
"<loc_236>": 50505,
|
169 |
+
"<loc_237>": 50506,
|
170 |
+
"<loc_238>": 50507,
|
171 |
+
"<loc_239>": 50508,
|
172 |
+
"<loc_23>": 50292,
|
173 |
+
"<loc_240>": 50509,
|
174 |
+
"<loc_241>": 50510,
|
175 |
+
"<loc_242>": 50511,
|
176 |
+
"<loc_243>": 50512,
|
177 |
+
"<loc_244>": 50513,
|
178 |
+
"<loc_245>": 50514,
|
179 |
+
"<loc_246>": 50515,
|
180 |
+
"<loc_247>": 50516,
|
181 |
+
"<loc_248>": 50517,
|
182 |
+
"<loc_249>": 50518,
|
183 |
+
"<loc_24>": 50293,
|
184 |
+
"<loc_250>": 50519,
|
185 |
+
"<loc_251>": 50520,
|
186 |
+
"<loc_252>": 50521,
|
187 |
+
"<loc_253>": 50522,
|
188 |
+
"<loc_254>": 50523,
|
189 |
+
"<loc_255>": 50524,
|
190 |
+
"<loc_256>": 50525,
|
191 |
+
"<loc_257>": 50526,
|
192 |
+
"<loc_258>": 50527,
|
193 |
+
"<loc_259>": 50528,
|
194 |
+
"<loc_25>": 50294,
|
195 |
+
"<loc_260>": 50529,
|
196 |
+
"<loc_261>": 50530,
|
197 |
+
"<loc_262>": 50531,
|
198 |
+
"<loc_263>": 50532,
|
199 |
+
"<loc_264>": 50533,
|
200 |
+
"<loc_265>": 50534,
|
201 |
+
"<loc_266>": 50535,
|
202 |
+
"<loc_267>": 50536,
|
203 |
+
"<loc_268>": 50537,
|
204 |
+
"<loc_269>": 50538,
|
205 |
+
"<loc_26>": 50295,
|
206 |
+
"<loc_270>": 50539,
|
207 |
+
"<loc_271>": 50540,
|
208 |
+
"<loc_272>": 50541,
|
209 |
+
"<loc_273>": 50542,
|
210 |
+
"<loc_274>": 50543,
|
211 |
+
"<loc_275>": 50544,
|
212 |
+
"<loc_276>": 50545,
|
213 |
+
"<loc_277>": 50546,
|
214 |
+
"<loc_278>": 50547,
|
215 |
+
"<loc_279>": 50548,
|
216 |
+
"<loc_27>": 50296,
|
217 |
+
"<loc_280>": 50549,
|
218 |
+
"<loc_281>": 50550,
|
219 |
+
"<loc_282>": 50551,
|
220 |
+
"<loc_283>": 50552,
|
221 |
+
"<loc_284>": 50553,
|
222 |
+
"<loc_285>": 50554,
|
223 |
+
"<loc_286>": 50555,
|
224 |
+
"<loc_287>": 50556,
|
225 |
+
"<loc_288>": 50557,
|
226 |
+
"<loc_289>": 50558,
|
227 |
+
"<loc_28>": 50297,
|
228 |
+
"<loc_290>": 50559,
|
229 |
+
"<loc_291>": 50560,
|
230 |
+
"<loc_292>": 50561,
|
231 |
+
"<loc_293>": 50562,
|
232 |
+
"<loc_294>": 50563,
|
233 |
+
"<loc_295>": 50564,
|
234 |
+
"<loc_296>": 50565,
|
235 |
+
"<loc_297>": 50566,
|
236 |
+
"<loc_298>": 50567,
|
237 |
+
"<loc_299>": 50568,
|
238 |
+
"<loc_29>": 50298,
|
239 |
+
"<loc_2>": 50271,
|
240 |
+
"<loc_300>": 50569,
|
241 |
+
"<loc_301>": 50570,
|
242 |
+
"<loc_302>": 50571,
|
243 |
+
"<loc_303>": 50572,
|
244 |
+
"<loc_304>": 50573,
|
245 |
+
"<loc_305>": 50574,
|
246 |
+
"<loc_306>": 50575,
|
247 |
+
"<loc_307>": 50576,
|
248 |
+
"<loc_308>": 50577,
|
249 |
+
"<loc_309>": 50578,
|
250 |
+
"<loc_30>": 50299,
|
251 |
+
"<loc_310>": 50579,
|
252 |
+
"<loc_311>": 50580,
|
253 |
+
"<loc_312>": 50581,
|
254 |
+
"<loc_313>": 50582,
|
255 |
+
"<loc_314>": 50583,
|
256 |
+
"<loc_315>": 50584,
|
257 |
+
"<loc_316>": 50585,
|
258 |
+
"<loc_317>": 50586,
|
259 |
+
"<loc_318>": 50587,
|
260 |
+
"<loc_319>": 50588,
|
261 |
+
"<loc_31>": 50300,
|
262 |
+
"<loc_320>": 50589,
|
263 |
+
"<loc_321>": 50590,
|
264 |
+
"<loc_322>": 50591,
|
265 |
+
"<loc_323>": 50592,
|
266 |
+
"<loc_324>": 50593,
|
267 |
+
"<loc_325>": 50594,
|
268 |
+
"<loc_326>": 50595,
|
269 |
+
"<loc_327>": 50596,
|
270 |
+
"<loc_328>": 50597,
|
271 |
+
"<loc_329>": 50598,
|
272 |
+
"<loc_32>": 50301,
|
273 |
+
"<loc_330>": 50599,
|
274 |
+
"<loc_331>": 50600,
|
275 |
+
"<loc_332>": 50601,
|
276 |
+
"<loc_333>": 50602,
|
277 |
+
"<loc_334>": 50603,
|
278 |
+
"<loc_335>": 50604,
|
279 |
+
"<loc_336>": 50605,
|
280 |
+
"<loc_337>": 50606,
|
281 |
+
"<loc_338>": 50607,
|
282 |
+
"<loc_339>": 50608,
|
283 |
+
"<loc_33>": 50302,
|
284 |
+
"<loc_340>": 50609,
|
285 |
+
"<loc_341>": 50610,
|
286 |
+
"<loc_342>": 50611,
|
287 |
+
"<loc_343>": 50612,
|
288 |
+
"<loc_344>": 50613,
|
289 |
+
"<loc_345>": 50614,
|
290 |
+
"<loc_346>": 50615,
|
291 |
+
"<loc_347>": 50616,
|
292 |
+
"<loc_348>": 50617,
|
293 |
+
"<loc_349>": 50618,
|
294 |
+
"<loc_34>": 50303,
|
295 |
+
"<loc_350>": 50619,
|
296 |
+
"<loc_351>": 50620,
|
297 |
+
"<loc_352>": 50621,
|
298 |
+
"<loc_353>": 50622,
|
299 |
+
"<loc_354>": 50623,
|
300 |
+
"<loc_355>": 50624,
|
301 |
+
"<loc_356>": 50625,
|
302 |
+
"<loc_357>": 50626,
|
303 |
+
"<loc_358>": 50627,
|
304 |
+
"<loc_359>": 50628,
|
305 |
+
"<loc_35>": 50304,
|
306 |
+
"<loc_360>": 50629,
|
307 |
+
"<loc_361>": 50630,
|
308 |
+
"<loc_362>": 50631,
|
309 |
+
"<loc_363>": 50632,
|
310 |
+
"<loc_364>": 50633,
|
311 |
+
"<loc_365>": 50634,
|
312 |
+
"<loc_366>": 50635,
|
313 |
+
"<loc_367>": 50636,
|
314 |
+
"<loc_368>": 50637,
|
315 |
+
"<loc_369>": 50638,
|
316 |
+
"<loc_36>": 50305,
|
317 |
+
"<loc_370>": 50639,
|
318 |
+
"<loc_371>": 50640,
|
319 |
+
"<loc_372>": 50641,
|
320 |
+
"<loc_373>": 50642,
|
321 |
+
"<loc_374>": 50643,
|
322 |
+
"<loc_375>": 50644,
|
323 |
+
"<loc_376>": 50645,
|
324 |
+
"<loc_377>": 50646,
|
325 |
+
"<loc_378>": 50647,
|
326 |
+
"<loc_379>": 50648,
|
327 |
+
"<loc_37>": 50306,
|
328 |
+
"<loc_380>": 50649,
|
329 |
+
"<loc_381>": 50650,
|
330 |
+
"<loc_382>": 50651,
|
331 |
+
"<loc_383>": 50652,
|
332 |
+
"<loc_384>": 50653,
|
333 |
+
"<loc_385>": 50654,
|
334 |
+
"<loc_386>": 50655,
|
335 |
+
"<loc_387>": 50656,
|
336 |
+
"<loc_388>": 50657,
|
337 |
+
"<loc_389>": 50658,
|
338 |
+
"<loc_38>": 50307,
|
339 |
+
"<loc_390>": 50659,
|
340 |
+
"<loc_391>": 50660,
|
341 |
+
"<loc_392>": 50661,
|
342 |
+
"<loc_393>": 50662,
|
343 |
+
"<loc_394>": 50663,
|
344 |
+
"<loc_395>": 50664,
|
345 |
+
"<loc_396>": 50665,
|
346 |
+
"<loc_397>": 50666,
|
347 |
+
"<loc_398>": 50667,
|
348 |
+
"<loc_399>": 50668,
|
349 |
+
"<loc_39>": 50308,
|
350 |
+
"<loc_3>": 50272,
|
351 |
+
"<loc_400>": 50669,
|
352 |
+
"<loc_401>": 50670,
|
353 |
+
"<loc_402>": 50671,
|
354 |
+
"<loc_403>": 50672,
|
355 |
+
"<loc_404>": 50673,
|
356 |
+
"<loc_405>": 50674,
|
357 |
+
"<loc_406>": 50675,
|
358 |
+
"<loc_407>": 50676,
|
359 |
+
"<loc_408>": 50677,
|
360 |
+
"<loc_409>": 50678,
|
361 |
+
"<loc_40>": 50309,
|
362 |
+
"<loc_410>": 50679,
|
363 |
+
"<loc_411>": 50680,
|
364 |
+
"<loc_412>": 50681,
|
365 |
+
"<loc_413>": 50682,
|
366 |
+
"<loc_414>": 50683,
|
367 |
+
"<loc_415>": 50684,
|
368 |
+
"<loc_416>": 50685,
|
369 |
+
"<loc_417>": 50686,
|
370 |
+
"<loc_418>": 50687,
|
371 |
+
"<loc_419>": 50688,
|
372 |
+
"<loc_41>": 50310,
|
373 |
+
"<loc_420>": 50689,
|
374 |
+
"<loc_421>": 50690,
|
375 |
+
"<loc_422>": 50691,
|
376 |
+
"<loc_423>": 50692,
|
377 |
+
"<loc_424>": 50693,
|
378 |
+
"<loc_425>": 50694,
|
379 |
+
"<loc_426>": 50695,
|
380 |
+
"<loc_427>": 50696,
|
381 |
+
"<loc_428>": 50697,
|
382 |
+
"<loc_429>": 50698,
|
383 |
+
"<loc_42>": 50311,
|
384 |
+
"<loc_430>": 50699,
|
385 |
+
"<loc_431>": 50700,
|
386 |
+
"<loc_432>": 50701,
|
387 |
+
"<loc_433>": 50702,
|
388 |
+
"<loc_434>": 50703,
|
389 |
+
"<loc_435>": 50704,
|
390 |
+
"<loc_436>": 50705,
|
391 |
+
"<loc_437>": 50706,
|
392 |
+
"<loc_438>": 50707,
|
393 |
+
"<loc_439>": 50708,
|
394 |
+
"<loc_43>": 50312,
|
395 |
+
"<loc_440>": 50709,
|
396 |
+
"<loc_441>": 50710,
|
397 |
+
"<loc_442>": 50711,
|
398 |
+
"<loc_443>": 50712,
|
399 |
+
"<loc_444>": 50713,
|
400 |
+
"<loc_445>": 50714,
|
401 |
+
"<loc_446>": 50715,
|
402 |
+
"<loc_447>": 50716,
|
403 |
+
"<loc_448>": 50717,
|
404 |
+
"<loc_449>": 50718,
|
405 |
+
"<loc_44>": 50313,
|
406 |
+
"<loc_450>": 50719,
|
407 |
+
"<loc_451>": 50720,
|
408 |
+
"<loc_452>": 50721,
|
409 |
+
"<loc_453>": 50722,
|
410 |
+
"<loc_454>": 50723,
|
411 |
+
"<loc_455>": 50724,
|
412 |
+
"<loc_456>": 50725,
|
413 |
+
"<loc_457>": 50726,
|
414 |
+
"<loc_458>": 50727,
|
415 |
+
"<loc_459>": 50728,
|
416 |
+
"<loc_45>": 50314,
|
417 |
+
"<loc_460>": 50729,
|
418 |
+
"<loc_461>": 50730,
|
419 |
+
"<loc_462>": 50731,
|
420 |
+
"<loc_463>": 50732,
|
421 |
+
"<loc_464>": 50733,
|
422 |
+
"<loc_465>": 50734,
|
423 |
+
"<loc_466>": 50735,
|
424 |
+
"<loc_467>": 50736,
|
425 |
+
"<loc_468>": 50737,
|
426 |
+
"<loc_469>": 50738,
|
427 |
+
"<loc_46>": 50315,
|
428 |
+
"<loc_470>": 50739,
|
429 |
+
"<loc_471>": 50740,
|
430 |
+
"<loc_472>": 50741,
|
431 |
+
"<loc_473>": 50742,
|
432 |
+
"<loc_474>": 50743,
|
433 |
+
"<loc_475>": 50744,
|
434 |
+
"<loc_476>": 50745,
|
435 |
+
"<loc_477>": 50746,
|
436 |
+
"<loc_478>": 50747,
|
437 |
+
"<loc_479>": 50748,
|
438 |
+
"<loc_47>": 50316,
|
439 |
+
"<loc_480>": 50749,
|
440 |
+
"<loc_481>": 50750,
|
441 |
+
"<loc_482>": 50751,
|
442 |
+
"<loc_483>": 50752,
|
443 |
+
"<loc_484>": 50753,
|
444 |
+
"<loc_485>": 50754,
|
445 |
+
"<loc_486>": 50755,
|
446 |
+
"<loc_487>": 50756,
|
447 |
+
"<loc_488>": 50757,
|
448 |
+
"<loc_489>": 50758,
|
449 |
+
"<loc_48>": 50317,
|
450 |
+
"<loc_490>": 50759,
|
451 |
+
"<loc_491>": 50760,
|
452 |
+
"<loc_492>": 50761,
|
453 |
+
"<loc_493>": 50762,
|
454 |
+
"<loc_494>": 50763,
|
455 |
+
"<loc_495>": 50764,
|
456 |
+
"<loc_496>": 50765,
|
457 |
+
"<loc_497>": 50766,
|
458 |
+
"<loc_498>": 50767,
|
459 |
+
"<loc_499>": 50768,
|
460 |
+
"<loc_49>": 50318,
|
461 |
+
"<loc_4>": 50273,
|
462 |
+
"<loc_500>": 50769,
|
463 |
+
"<loc_501>": 50770,
|
464 |
+
"<loc_502>": 50771,
|
465 |
+
"<loc_503>": 50772,
|
466 |
+
"<loc_504>": 50773,
|
467 |
+
"<loc_505>": 50774,
|
468 |
+
"<loc_506>": 50775,
|
469 |
+
"<loc_507>": 50776,
|
470 |
+
"<loc_508>": 50777,
|
471 |
+
"<loc_509>": 50778,
|
472 |
+
"<loc_50>": 50319,
|
473 |
+
"<loc_510>": 50779,
|
474 |
+
"<loc_511>": 50780,
|
475 |
+
"<loc_512>": 50781,
|
476 |
+
"<loc_513>": 50782,
|
477 |
+
"<loc_514>": 50783,
|
478 |
+
"<loc_515>": 50784,
|
479 |
+
"<loc_516>": 50785,
|
480 |
+
"<loc_517>": 50786,
|
481 |
+
"<loc_518>": 50787,
|
482 |
+
"<loc_519>": 50788,
|
483 |
+
"<loc_51>": 50320,
|
484 |
+
"<loc_520>": 50789,
|
485 |
+
"<loc_521>": 50790,
|
486 |
+
"<loc_522>": 50791,
|
487 |
+
"<loc_523>": 50792,
|
488 |
+
"<loc_524>": 50793,
|
489 |
+
"<loc_525>": 50794,
|
490 |
+
"<loc_526>": 50795,
|
491 |
+
"<loc_527>": 50796,
|
492 |
+
"<loc_528>": 50797,
|
493 |
+
"<loc_529>": 50798,
|
494 |
+
"<loc_52>": 50321,
|
495 |
+
"<loc_530>": 50799,
|
496 |
+
"<loc_531>": 50800,
|
497 |
+
"<loc_532>": 50801,
|
498 |
+
"<loc_533>": 50802,
|
499 |
+
"<loc_534>": 50803,
|
500 |
+
"<loc_535>": 50804,
|
501 |
+
"<loc_536>": 50805,
|
502 |
+
"<loc_537>": 50806,
|
503 |
+
"<loc_538>": 50807,
|
504 |
+
"<loc_539>": 50808,
|
505 |
+
"<loc_53>": 50322,
|
506 |
+
"<loc_540>": 50809,
|
507 |
+
"<loc_541>": 50810,
|
508 |
+
"<loc_542>": 50811,
|
509 |
+
"<loc_543>": 50812,
|
510 |
+
"<loc_544>": 50813,
|
511 |
+
"<loc_545>": 50814,
|
512 |
+
"<loc_546>": 50815,
|
513 |
+
"<loc_547>": 50816,
|
514 |
+
"<loc_548>": 50817,
|
515 |
+
"<loc_549>": 50818,
|
516 |
+
"<loc_54>": 50323,
|
517 |
+
"<loc_550>": 50819,
|
518 |
+
"<loc_551>": 50820,
|
519 |
+
"<loc_552>": 50821,
|
520 |
+
"<loc_553>": 50822,
|
521 |
+
"<loc_554>": 50823,
|
522 |
+
"<loc_555>": 50824,
|
523 |
+
"<loc_556>": 50825,
|
524 |
+
"<loc_557>": 50826,
|
525 |
+
"<loc_558>": 50827,
|
526 |
+
"<loc_559>": 50828,
|
527 |
+
"<loc_55>": 50324,
|
528 |
+
"<loc_560>": 50829,
|
529 |
+
"<loc_561>": 50830,
|
530 |
+
"<loc_562>": 50831,
|
531 |
+
"<loc_563>": 50832,
|
532 |
+
"<loc_564>": 50833,
|
533 |
+
"<loc_565>": 50834,
|
534 |
+
"<loc_566>": 50835,
|
535 |
+
"<loc_567>": 50836,
|
536 |
+
"<loc_568>": 50837,
|
537 |
+
"<loc_569>": 50838,
|
538 |
+
"<loc_56>": 50325,
|
539 |
+
"<loc_570>": 50839,
|
540 |
+
"<loc_571>": 50840,
|
541 |
+
"<loc_572>": 50841,
|
542 |
+
"<loc_573>": 50842,
|
543 |
+
"<loc_574>": 50843,
|
544 |
+
"<loc_575>": 50844,
|
545 |
+
"<loc_576>": 50845,
|
546 |
+
"<loc_577>": 50846,
|
547 |
+
"<loc_578>": 50847,
|
548 |
+
"<loc_579>": 50848,
|
549 |
+
"<loc_57>": 50326,
|
550 |
+
"<loc_580>": 50849,
|
551 |
+
"<loc_581>": 50850,
|
552 |
+
"<loc_582>": 50851,
|
553 |
+
"<loc_583>": 50852,
|
554 |
+
"<loc_584>": 50853,
|
555 |
+
"<loc_585>": 50854,
|
556 |
+
"<loc_586>": 50855,
|
557 |
+
"<loc_587>": 50856,
|
558 |
+
"<loc_588>": 50857,
|
559 |
+
"<loc_589>": 50858,
|
560 |
+
"<loc_58>": 50327,
|
561 |
+
"<loc_590>": 50859,
|
562 |
+
"<loc_591>": 50860,
|
563 |
+
"<loc_592>": 50861,
|
564 |
+
"<loc_593>": 50862,
|
565 |
+
"<loc_594>": 50863,
|
566 |
+
"<loc_595>": 50864,
|
567 |
+
"<loc_596>": 50865,
|
568 |
+
"<loc_597>": 50866,
|
569 |
+
"<loc_598>": 50867,
|
570 |
+
"<loc_599>": 50868,
|
571 |
+
"<loc_59>": 50328,
|
572 |
+
"<loc_5>": 50274,
|
573 |
+
"<loc_600>": 50869,
|
574 |
+
"<loc_601>": 50870,
|
575 |
+
"<loc_602>": 50871,
|
576 |
+
"<loc_603>": 50872,
|
577 |
+
"<loc_604>": 50873,
|
578 |
+
"<loc_605>": 50874,
|
579 |
+
"<loc_606>": 50875,
|
580 |
+
"<loc_607>": 50876,
|
581 |
+
"<loc_608>": 50877,
|
582 |
+
"<loc_609>": 50878,
|
583 |
+
"<loc_60>": 50329,
|
584 |
+
"<loc_610>": 50879,
|
585 |
+
"<loc_611>": 50880,
|
586 |
+
"<loc_612>": 50881,
|
587 |
+
"<loc_613>": 50882,
|
588 |
+
"<loc_614>": 50883,
|
589 |
+
"<loc_615>": 50884,
|
590 |
+
"<loc_616>": 50885,
|
591 |
+
"<loc_617>": 50886,
|
592 |
+
"<loc_618>": 50887,
|
593 |
+
"<loc_619>": 50888,
|
594 |
+
"<loc_61>": 50330,
|
595 |
+
"<loc_620>": 50889,
|
596 |
+
"<loc_621>": 50890,
|
597 |
+
"<loc_622>": 50891,
|
598 |
+
"<loc_623>": 50892,
|
599 |
+
"<loc_624>": 50893,
|
600 |
+
"<loc_625>": 50894,
|
601 |
+
"<loc_626>": 50895,
|
602 |
+
"<loc_627>": 50896,
|
603 |
+
"<loc_628>": 50897,
|
604 |
+
"<loc_629>": 50898,
|
605 |
+
"<loc_62>": 50331,
|
606 |
+
"<loc_630>": 50899,
|
607 |
+
"<loc_631>": 50900,
|
608 |
+
"<loc_632>": 50901,
|
609 |
+
"<loc_633>": 50902,
|
610 |
+
"<loc_634>": 50903,
|
611 |
+
"<loc_635>": 50904,
|
612 |
+
"<loc_636>": 50905,
|
613 |
+
"<loc_637>": 50906,
|
614 |
+
"<loc_638>": 50907,
|
615 |
+
"<loc_639>": 50908,
|
616 |
+
"<loc_63>": 50332,
|
617 |
+
"<loc_640>": 50909,
|
618 |
+
"<loc_641>": 50910,
|
619 |
+
"<loc_642>": 50911,
|
620 |
+
"<loc_643>": 50912,
|
621 |
+
"<loc_644>": 50913,
|
622 |
+
"<loc_645>": 50914,
|
623 |
+
"<loc_646>": 50915,
|
624 |
+
"<loc_647>": 50916,
|
625 |
+
"<loc_648>": 50917,
|
626 |
+
"<loc_649>": 50918,
|
627 |
+
"<loc_64>": 50333,
|
628 |
+
"<loc_650>": 50919,
|
629 |
+
"<loc_651>": 50920,
|
630 |
+
"<loc_652>": 50921,
|
631 |
+
"<loc_653>": 50922,
|
632 |
+
"<loc_654>": 50923,
|
633 |
+
"<loc_655>": 50924,
|
634 |
+
"<loc_656>": 50925,
|
635 |
+
"<loc_657>": 50926,
|
636 |
+
"<loc_658>": 50927,
|
637 |
+
"<loc_659>": 50928,
|
638 |
+
"<loc_65>": 50334,
|
639 |
+
"<loc_660>": 50929,
|
640 |
+
"<loc_661>": 50930,
|
641 |
+
"<loc_662>": 50931,
|
642 |
+
"<loc_663>": 50932,
|
643 |
+
"<loc_664>": 50933,
|
644 |
+
"<loc_665>": 50934,
|
645 |
+
"<loc_666>": 50935,
|
646 |
+
"<loc_667>": 50936,
|
647 |
+
"<loc_668>": 50937,
|
648 |
+
"<loc_669>": 50938,
|
649 |
+
"<loc_66>": 50335,
|
650 |
+
"<loc_670>": 50939,
|
651 |
+
"<loc_671>": 50940,
|
652 |
+
"<loc_672>": 50941,
|
653 |
+
"<loc_673>": 50942,
|
654 |
+
"<loc_674>": 50943,
|
655 |
+
"<loc_675>": 50944,
|
656 |
+
"<loc_676>": 50945,
|
657 |
+
"<loc_677>": 50946,
|
658 |
+
"<loc_678>": 50947,
|
659 |
+
"<loc_679>": 50948,
|
660 |
+
"<loc_67>": 50336,
|
661 |
+
"<loc_680>": 50949,
|
662 |
+
"<loc_681>": 50950,
|
663 |
+
"<loc_682>": 50951,
|
664 |
+
"<loc_683>": 50952,
|
665 |
+
"<loc_684>": 50953,
|
666 |
+
"<loc_685>": 50954,
|
667 |
+
"<loc_686>": 50955,
|
668 |
+
"<loc_687>": 50956,
|
669 |
+
"<loc_688>": 50957,
|
670 |
+
"<loc_689>": 50958,
|
671 |
+
"<loc_68>": 50337,
|
672 |
+
"<loc_690>": 50959,
|
673 |
+
"<loc_691>": 50960,
|
674 |
+
"<loc_692>": 50961,
|
675 |
+
"<loc_693>": 50962,
|
676 |
+
"<loc_694>": 50963,
|
677 |
+
"<loc_695>": 50964,
|
678 |
+
"<loc_696>": 50965,
|
679 |
+
"<loc_697>": 50966,
|
680 |
+
"<loc_698>": 50967,
|
681 |
+
"<loc_699>": 50968,
|
682 |
+
"<loc_69>": 50338,
|
683 |
+
"<loc_6>": 50275,
|
684 |
+
"<loc_700>": 50969,
|
685 |
+
"<loc_701>": 50970,
|
686 |
+
"<loc_702>": 50971,
|
687 |
+
"<loc_703>": 50972,
|
688 |
+
"<loc_704>": 50973,
|
689 |
+
"<loc_705>": 50974,
|
690 |
+
"<loc_706>": 50975,
|
691 |
+
"<loc_707>": 50976,
|
692 |
+
"<loc_708>": 50977,
|
693 |
+
"<loc_709>": 50978,
|
694 |
+
"<loc_70>": 50339,
|
695 |
+
"<loc_710>": 50979,
|
696 |
+
"<loc_711>": 50980,
|
697 |
+
"<loc_712>": 50981,
|
698 |
+
"<loc_713>": 50982,
|
699 |
+
"<loc_714>": 50983,
|
700 |
+
"<loc_715>": 50984,
|
701 |
+
"<loc_716>": 50985,
|
702 |
+
"<loc_717>": 50986,
|
703 |
+
"<loc_718>": 50987,
|
704 |
+
"<loc_719>": 50988,
|
705 |
+
"<loc_71>": 50340,
|
706 |
+
"<loc_720>": 50989,
|
707 |
+
"<loc_721>": 50990,
|
708 |
+
"<loc_722>": 50991,
|
709 |
+
"<loc_723>": 50992,
|
710 |
+
"<loc_724>": 50993,
|
711 |
+
"<loc_725>": 50994,
|
712 |
+
"<loc_726>": 50995,
|
713 |
+
"<loc_727>": 50996,
|
714 |
+
"<loc_728>": 50997,
|
715 |
+
"<loc_729>": 50998,
|
716 |
+
"<loc_72>": 50341,
|
717 |
+
"<loc_730>": 50999,
|
718 |
+
"<loc_731>": 51000,
|
719 |
+
"<loc_732>": 51001,
|
720 |
+
"<loc_733>": 51002,
|
721 |
+
"<loc_734>": 51003,
|
722 |
+
"<loc_735>": 51004,
|
723 |
+
"<loc_736>": 51005,
|
724 |
+
"<loc_737>": 51006,
|
725 |
+
"<loc_738>": 51007,
|
726 |
+
"<loc_739>": 51008,
|
727 |
+
"<loc_73>": 50342,
|
728 |
+
"<loc_740>": 51009,
|
729 |
+
"<loc_741>": 51010,
|
730 |
+
"<loc_742>": 51011,
|
731 |
+
"<loc_743>": 51012,
|
732 |
+
"<loc_744>": 51013,
|
733 |
+
"<loc_745>": 51014,
|
734 |
+
"<loc_746>": 51015,
|
735 |
+
"<loc_747>": 51016,
|
736 |
+
"<loc_748>": 51017,
|
737 |
+
"<loc_749>": 51018,
|
738 |
+
"<loc_74>": 50343,
|
739 |
+
"<loc_750>": 51019,
|
740 |
+
"<loc_751>": 51020,
|
741 |
+
"<loc_752>": 51021,
|
742 |
+
"<loc_753>": 51022,
|
743 |
+
"<loc_754>": 51023,
|
744 |
+
"<loc_755>": 51024,
|
745 |
+
"<loc_756>": 51025,
|
746 |
+
"<loc_757>": 51026,
|
747 |
+
"<loc_758>": 51027,
|
748 |
+
"<loc_759>": 51028,
|
749 |
+
"<loc_75>": 50344,
|
750 |
+
"<loc_760>": 51029,
|
751 |
+
"<loc_761>": 51030,
|
752 |
+
"<loc_762>": 51031,
|
753 |
+
"<loc_763>": 51032,
|
754 |
+
"<loc_764>": 51033,
|
755 |
+
"<loc_765>": 51034,
|
756 |
+
"<loc_766>": 51035,
|
757 |
+
"<loc_767>": 51036,
|
758 |
+
"<loc_768>": 51037,
|
759 |
+
"<loc_769>": 51038,
|
760 |
+
"<loc_76>": 50345,
|
761 |
+
"<loc_770>": 51039,
|
762 |
+
"<loc_771>": 51040,
|
763 |
+
"<loc_772>": 51041,
|
764 |
+
"<loc_773>": 51042,
|
765 |
+
"<loc_774>": 51043,
|
766 |
+
"<loc_775>": 51044,
|
767 |
+
"<loc_776>": 51045,
|
768 |
+
"<loc_777>": 51046,
|
769 |
+
"<loc_778>": 51047,
|
770 |
+
"<loc_779>": 51048,
|
771 |
+
"<loc_77>": 50346,
|
772 |
+
"<loc_780>": 51049,
|
773 |
+
"<loc_781>": 51050,
|
774 |
+
"<loc_782>": 51051,
|
775 |
+
"<loc_783>": 51052,
|
776 |
+
"<loc_784>": 51053,
|
777 |
+
"<loc_785>": 51054,
|
778 |
+
"<loc_786>": 51055,
|
779 |
+
"<loc_787>": 51056,
|
780 |
+
"<loc_788>": 51057,
|
781 |
+
"<loc_789>": 51058,
|
782 |
+
"<loc_78>": 50347,
|
783 |
+
"<loc_790>": 51059,
|
784 |
+
"<loc_791>": 51060,
|
785 |
+
"<loc_792>": 51061,
|
786 |
+
"<loc_793>": 51062,
|
787 |
+
"<loc_794>": 51063,
|
788 |
+
"<loc_795>": 51064,
|
789 |
+
"<loc_796>": 51065,
|
790 |
+
"<loc_797>": 51066,
|
791 |
+
"<loc_798>": 51067,
|
792 |
+
"<loc_799>": 51068,
|
793 |
+
"<loc_79>": 50348,
|
794 |
+
"<loc_7>": 50276,
|
795 |
+
"<loc_800>": 51069,
|
796 |
+
"<loc_801>": 51070,
|
797 |
+
"<loc_802>": 51071,
|
798 |
+
"<loc_803>": 51072,
|
799 |
+
"<loc_804>": 51073,
|
800 |
+
"<loc_805>": 51074,
|
801 |
+
"<loc_806>": 51075,
|
802 |
+
"<loc_807>": 51076,
|
803 |
+
"<loc_808>": 51077,
|
804 |
+
"<loc_809>": 51078,
|
805 |
+
"<loc_80>": 50349,
|
806 |
+
"<loc_810>": 51079,
|
807 |
+
"<loc_811>": 51080,
|
808 |
+
"<loc_812>": 51081,
|
809 |
+
"<loc_813>": 51082,
|
810 |
+
"<loc_814>": 51083,
|
811 |
+
"<loc_815>": 51084,
|
812 |
+
"<loc_816>": 51085,
|
813 |
+
"<loc_817>": 51086,
|
814 |
+
"<loc_818>": 51087,
|
815 |
+
"<loc_819>": 51088,
|
816 |
+
"<loc_81>": 50350,
|
817 |
+
"<loc_820>": 51089,
|
818 |
+
"<loc_821>": 51090,
|
819 |
+
"<loc_822>": 51091,
|
820 |
+
"<loc_823>": 51092,
|
821 |
+
"<loc_824>": 51093,
|
822 |
+
"<loc_825>": 51094,
|
823 |
+
"<loc_826>": 51095,
|
824 |
+
"<loc_827>": 51096,
|
825 |
+
"<loc_828>": 51097,
|
826 |
+
"<loc_829>": 51098,
|
827 |
+
"<loc_82>": 50351,
|
828 |
+
"<loc_830>": 51099,
|
829 |
+
"<loc_831>": 51100,
|
830 |
+
"<loc_832>": 51101,
|
831 |
+
"<loc_833>": 51102,
|
832 |
+
"<loc_834>": 51103,
|
833 |
+
"<loc_835>": 51104,
|
834 |
+
"<loc_836>": 51105,
|
835 |
+
"<loc_837>": 51106,
|
836 |
+
"<loc_838>": 51107,
|
837 |
+
"<loc_839>": 51108,
|
838 |
+
"<loc_83>": 50352,
|
839 |
+
"<loc_840>": 51109,
|
840 |
+
"<loc_841>": 51110,
|
841 |
+
"<loc_842>": 51111,
|
842 |
+
"<loc_843>": 51112,
|
843 |
+
"<loc_844>": 51113,
|
844 |
+
"<loc_845>": 51114,
|
845 |
+
"<loc_846>": 51115,
|
846 |
+
"<loc_847>": 51116,
|
847 |
+
"<loc_848>": 51117,
|
848 |
+
"<loc_849>": 51118,
|
849 |
+
"<loc_84>": 50353,
|
850 |
+
"<loc_850>": 51119,
|
851 |
+
"<loc_851>": 51120,
|
852 |
+
"<loc_852>": 51121,
|
853 |
+
"<loc_853>": 51122,
|
854 |
+
"<loc_854>": 51123,
|
855 |
+
"<loc_855>": 51124,
|
856 |
+
"<loc_856>": 51125,
|
857 |
+
"<loc_857>": 51126,
|
858 |
+
"<loc_858>": 51127,
|
859 |
+
"<loc_859>": 51128,
|
860 |
+
"<loc_85>": 50354,
|
861 |
+
"<loc_860>": 51129,
|
862 |
+
"<loc_861>": 51130,
|
863 |
+
"<loc_862>": 51131,
|
864 |
+
"<loc_863>": 51132,
|
865 |
+
"<loc_864>": 51133,
|
866 |
+
"<loc_865>": 51134,
|
867 |
+
"<loc_866>": 51135,
|
868 |
+
"<loc_867>": 51136,
|
869 |
+
"<loc_868>": 51137,
|
870 |
+
"<loc_869>": 51138,
|
871 |
+
"<loc_86>": 50355,
|
872 |
+
"<loc_870>": 51139,
|
873 |
+
"<loc_871>": 51140,
|
874 |
+
"<loc_872>": 51141,
|
875 |
+
"<loc_873>": 51142,
|
876 |
+
"<loc_874>": 51143,
|
877 |
+
"<loc_875>": 51144,
|
878 |
+
"<loc_876>": 51145,
|
879 |
+
"<loc_877>": 51146,
|
880 |
+
"<loc_878>": 51147,
|
881 |
+
"<loc_879>": 51148,
|
882 |
+
"<loc_87>": 50356,
|
883 |
+
"<loc_880>": 51149,
|
884 |
+
"<loc_881>": 51150,
|
885 |
+
"<loc_882>": 51151,
|
886 |
+
"<loc_883>": 51152,
|
887 |
+
"<loc_884>": 51153,
|
888 |
+
"<loc_885>": 51154,
|
889 |
+
"<loc_886>": 51155,
|
890 |
+
"<loc_887>": 51156,
|
891 |
+
"<loc_888>": 51157,
|
892 |
+
"<loc_889>": 51158,
|
893 |
+
"<loc_88>": 50357,
|
894 |
+
"<loc_890>": 51159,
|
895 |
+
"<loc_891>": 51160,
|
896 |
+
"<loc_892>": 51161,
|
897 |
+
"<loc_893>": 51162,
|
898 |
+
"<loc_894>": 51163,
|
899 |
+
"<loc_895>": 51164,
|
900 |
+
"<loc_896>": 51165,
|
901 |
+
"<loc_897>": 51166,
|
902 |
+
"<loc_898>": 51167,
|
903 |
+
"<loc_899>": 51168,
|
904 |
+
"<loc_89>": 50358,
|
905 |
+
"<loc_8>": 50277,
|
906 |
+
"<loc_900>": 51169,
|
907 |
+
"<loc_901>": 51170,
|
908 |
+
"<loc_902>": 51171,
|
909 |
+
"<loc_903>": 51172,
|
910 |
+
"<loc_904>": 51173,
|
911 |
+
"<loc_905>": 51174,
|
912 |
+
"<loc_906>": 51175,
|
913 |
+
"<loc_907>": 51176,
|
914 |
+
"<loc_908>": 51177,
|
915 |
+
"<loc_909>": 51178,
|
916 |
+
"<loc_90>": 50359,
|
917 |
+
"<loc_910>": 51179,
|
918 |
+
"<loc_911>": 51180,
|
919 |
+
"<loc_912>": 51181,
|
920 |
+
"<loc_913>": 51182,
|
921 |
+
"<loc_914>": 51183,
|
922 |
+
"<loc_915>": 51184,
|
923 |
+
"<loc_916>": 51185,
|
924 |
+
"<loc_917>": 51186,
|
925 |
+
"<loc_918>": 51187,
|
926 |
+
"<loc_919>": 51188,
|
927 |
+
"<loc_91>": 50360,
|
928 |
+
"<loc_920>": 51189,
|
929 |
+
"<loc_921>": 51190,
|
930 |
+
"<loc_922>": 51191,
|
931 |
+
"<loc_923>": 51192,
|
932 |
+
"<loc_924>": 51193,
|
933 |
+
"<loc_925>": 51194,
|
934 |
+
"<loc_926>": 51195,
|
935 |
+
"<loc_927>": 51196,
|
936 |
+
"<loc_928>": 51197,
|
937 |
+
"<loc_929>": 51198,
|
938 |
+
"<loc_92>": 50361,
|
939 |
+
"<loc_930>": 51199,
|
940 |
+
"<loc_931>": 51200,
|
941 |
+
"<loc_932>": 51201,
|
942 |
+
"<loc_933>": 51202,
|
943 |
+
"<loc_934>": 51203,
|
944 |
+
"<loc_935>": 51204,
|
945 |
+
"<loc_936>": 51205,
|
946 |
+
"<loc_937>": 51206,
|
947 |
+
"<loc_938>": 51207,
|
948 |
+
"<loc_939>": 51208,
|
949 |
+
"<loc_93>": 50362,
|
950 |
+
"<loc_940>": 51209,
|
951 |
+
"<loc_941>": 51210,
|
952 |
+
"<loc_942>": 51211,
|
953 |
+
"<loc_943>": 51212,
|
954 |
+
"<loc_944>": 51213,
|
955 |
+
"<loc_945>": 51214,
|
956 |
+
"<loc_946>": 51215,
|
957 |
+
"<loc_947>": 51216,
|
958 |
+
"<loc_948>": 51217,
|
959 |
+
"<loc_949>": 51218,
|
960 |
+
"<loc_94>": 50363,
|
961 |
+
"<loc_950>": 51219,
|
962 |
+
"<loc_951>": 51220,
|
963 |
+
"<loc_952>": 51221,
|
964 |
+
"<loc_953>": 51222,
|
965 |
+
"<loc_954>": 51223,
|
966 |
+
"<loc_955>": 51224,
|
967 |
+
"<loc_956>": 51225,
|
968 |
+
"<loc_957>": 51226,
|
969 |
+
"<loc_958>": 51227,
|
970 |
+
"<loc_959>": 51228,
|
971 |
+
"<loc_95>": 50364,
|
972 |
+
"<loc_960>": 51229,
|
973 |
+
"<loc_961>": 51230,
|
974 |
+
"<loc_962>": 51231,
|
975 |
+
"<loc_963>": 51232,
|
976 |
+
"<loc_964>": 51233,
|
977 |
+
"<loc_965>": 51234,
|
978 |
+
"<loc_966>": 51235,
|
979 |
+
"<loc_967>": 51236,
|
980 |
+
"<loc_968>": 51237,
|
981 |
+
"<loc_969>": 51238,
|
982 |
+
"<loc_96>": 50365,
|
983 |
+
"<loc_970>": 51239,
|
984 |
+
"<loc_971>": 51240,
|
985 |
+
"<loc_972>": 51241,
|
986 |
+
"<loc_973>": 51242,
|
987 |
+
"<loc_974>": 51243,
|
988 |
+
"<loc_975>": 51244,
|
989 |
+
"<loc_976>": 51245,
|
990 |
+
"<loc_977>": 51246,
|
991 |
+
"<loc_978>": 51247,
|
992 |
+
"<loc_979>": 51248,
|
993 |
+
"<loc_97>": 50366,
|
994 |
+
"<loc_980>": 51249,
|
995 |
+
"<loc_981>": 51250,
|
996 |
+
"<loc_982>": 51251,
|
997 |
+
"<loc_983>": 51252,
|
998 |
+
"<loc_984>": 51253,
|
999 |
+
"<loc_985>": 51254,
|
1000 |
+
"<loc_986>": 51255,
|
1001 |
+
"<loc_987>": 51256,
|
1002 |
+
"<loc_988>": 51257,
|
1003 |
+
"<loc_989>": 51258,
|
1004 |
+
"<loc_98>": 50367,
|
1005 |
+
"<loc_990>": 51259,
|
1006 |
+
"<loc_991>": 51260,
|
1007 |
+
"<loc_992>": 51261,
|
1008 |
+
"<loc_993>": 51262,
|
1009 |
+
"<loc_994>": 51263,
|
1010 |
+
"<loc_995>": 51264,
|
1011 |
+
"<loc_996>": 51265,
|
1012 |
+
"<loc_997>": 51266,
|
1013 |
+
"<loc_998>": 51267,
|
1014 |
+
"<loc_999>": 51268,
|
1015 |
+
"<loc_99>": 50368,
|
1016 |
+
"<loc_9>": 50278,
|
1017 |
+
"<ncap>": 51271,
|
1018 |
+
"<ocr>": 50267,
|
1019 |
+
"<od>": 50265,
|
1020 |
+
"<poly>": 51286,
|
1021 |
+
"<proposal>": 51284,
|
1022 |
+
"<region_cap>": 51280,
|
1023 |
+
"<region_to_desciption>": 51282,
|
1024 |
+
"<seg>": 51277,
|
1025 |
+
"<sep>": 51279
|
1026 |
+
}
|
vision_tower/config.json
ADDED
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/fsx_0/user/jiuhai/hub/models--microsoft--Florence-2-large-ft/snapshots/c669c6b8bfbd7f0193fcb31f997879045a3612f3",
|
3 |
+
"architectures": [
|
4 |
+
"Florence2ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"auto_map": {
|
7 |
+
"AutoConfig": "configuration_florence2.Florence2Config",
|
8 |
+
"AutoModelForCausalLM": "modeling_florence2.Florence2ForConditionalGeneration"
|
9 |
+
},
|
10 |
+
"bos_token_id": 0,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"ignore_index": -100,
|
13 |
+
"is_encoder_decoder": true,
|
14 |
+
"model_type": "florence2",
|
15 |
+
"pad_token_id": 1,
|
16 |
+
"projection_dim": 1024,
|
17 |
+
"text_config": {
|
18 |
+
"_name_or_path": "",
|
19 |
+
"activation_dropout": 0.1,
|
20 |
+
"activation_function": "gelu",
|
21 |
+
"add_bias_logits": false,
|
22 |
+
"add_cross_attention": false,
|
23 |
+
"add_final_layer_norm": false,
|
24 |
+
"architectures": null,
|
25 |
+
"attention_dropout": 0.1,
|
26 |
+
"bad_words_ids": null,
|
27 |
+
"begin_suppress_tokens": null,
|
28 |
+
"bos_token_id": 0,
|
29 |
+
"chunk_size_feed_forward": 0,
|
30 |
+
"classif_dropout": 0.1,
|
31 |
+
"classifier_dropout": 0.0,
|
32 |
+
"cross_attention_hidden_size": null,
|
33 |
+
"d_model": 1024,
|
34 |
+
"decoder_attention_heads": 16,
|
35 |
+
"decoder_ffn_dim": 4096,
|
36 |
+
"decoder_layerdrop": 0.0,
|
37 |
+
"decoder_layers": 12,
|
38 |
+
"decoder_start_token_id": 2,
|
39 |
+
"diversity_penalty": 0.0,
|
40 |
+
"do_sample": false,
|
41 |
+
"dropout": 0.1,
|
42 |
+
"early_stopping": true,
|
43 |
+
"encoder_attention_heads": 16,
|
44 |
+
"encoder_ffn_dim": 4096,
|
45 |
+
"encoder_layerdrop": 0.0,
|
46 |
+
"encoder_layers": 12,
|
47 |
+
"encoder_no_repeat_ngram_size": 0,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"exponential_decay_length_penalty": null,
|
50 |
+
"finetuning_task": null,
|
51 |
+
"forced_bos_token_id": 0,
|
52 |
+
"forced_eos_token_id": 2,
|
53 |
+
"gradient_checkpointing": false,
|
54 |
+
"id2label": {
|
55 |
+
"0": "LABEL_0",
|
56 |
+
"1": "LABEL_1",
|
57 |
+
"2": "LABEL_2"
|
58 |
+
},
|
59 |
+
"init_std": 0.02,
|
60 |
+
"is_decoder": false,
|
61 |
+
"is_encoder_decoder": true,
|
62 |
+
"label2id": {
|
63 |
+
"LABEL_0": 0,
|
64 |
+
"LABEL_1": 1,
|
65 |
+
"LABEL_2": 2
|
66 |
+
},
|
67 |
+
"length_penalty": 1.0,
|
68 |
+
"max_length": 20,
|
69 |
+
"max_position_embeddings": 1024,
|
70 |
+
"min_length": 0,
|
71 |
+
"model_type": "florence2_language",
|
72 |
+
"no_repeat_ngram_size": 3,
|
73 |
+
"normalize_before": false,
|
74 |
+
"num_beam_groups": 1,
|
75 |
+
"num_beams": 3,
|
76 |
+
"num_hidden_layers": 12,
|
77 |
+
"num_return_sequences": 1,
|
78 |
+
"output_attentions": false,
|
79 |
+
"output_hidden_states": false,
|
80 |
+
"output_scores": false,
|
81 |
+
"pad_token_id": 1,
|
82 |
+
"prefix": null,
|
83 |
+
"problem_type": null,
|
84 |
+
"pruned_heads": {},
|
85 |
+
"remove_invalid_values": false,
|
86 |
+
"repetition_penalty": 1.0,
|
87 |
+
"return_dict": true,
|
88 |
+
"return_dict_in_generate": false,
|
89 |
+
"scale_embedding": false,
|
90 |
+
"sep_token_id": null,
|
91 |
+
"suppress_tokens": null,
|
92 |
+
"task_specific_params": null,
|
93 |
+
"temperature": 1.0,
|
94 |
+
"tf_legacy_loss": false,
|
95 |
+
"tie_encoder_decoder": false,
|
96 |
+
"tie_word_embeddings": true,
|
97 |
+
"tokenizer_class": null,
|
98 |
+
"top_k": 50,
|
99 |
+
"top_p": 1.0,
|
100 |
+
"torch_dtype": null,
|
101 |
+
"torchscript": false,
|
102 |
+
"typical_p": 1.0,
|
103 |
+
"use_bfloat16": false,
|
104 |
+
"use_cache": true,
|
105 |
+
"vocab_size": 51289
|
106 |
+
},
|
107 |
+
"torch_dtype": "float32",
|
108 |
+
"transformers_version": "4.43.2",
|
109 |
+
"vision_config": {
|
110 |
+
"_name_or_path": "",
|
111 |
+
"add_cross_attention": false,
|
112 |
+
"architectures": null,
|
113 |
+
"bad_words_ids": null,
|
114 |
+
"begin_suppress_tokens": null,
|
115 |
+
"bos_token_id": null,
|
116 |
+
"chunk_size_feed_forward": 0,
|
117 |
+
"cross_attention_hidden_size": null,
|
118 |
+
"decoder_start_token_id": null,
|
119 |
+
"depths": [
|
120 |
+
1,
|
121 |
+
1,
|
122 |
+
9,
|
123 |
+
1
|
124 |
+
],
|
125 |
+
"dim_embed": [
|
126 |
+
256,
|
127 |
+
512,
|
128 |
+
1024,
|
129 |
+
2048
|
130 |
+
],
|
131 |
+
"diversity_penalty": 0.0,
|
132 |
+
"do_sample": false,
|
133 |
+
"drop_path_rate": 0.1,
|
134 |
+
"early_stopping": false,
|
135 |
+
"enable_checkpoint": false,
|
136 |
+
"encoder_no_repeat_ngram_size": 0,
|
137 |
+
"eos_token_id": null,
|
138 |
+
"exponential_decay_length_penalty": null,
|
139 |
+
"finetuning_task": null,
|
140 |
+
"forced_bos_token_id": null,
|
141 |
+
"forced_eos_token_id": null,
|
142 |
+
"id2label": {
|
143 |
+
"0": "LABEL_0",
|
144 |
+
"1": "LABEL_1"
|
145 |
+
},
|
146 |
+
"image_feature_source": [
|
147 |
+
"spatial_avg_pool",
|
148 |
+
"temporal_avg_pool"
|
149 |
+
],
|
150 |
+
"image_pos_embed": {
|
151 |
+
"max_pos_embeddings": 50,
|
152 |
+
"type": "learned_abs_2d"
|
153 |
+
},
|
154 |
+
"is_decoder": false,
|
155 |
+
"is_encoder_decoder": false,
|
156 |
+
"label2id": {
|
157 |
+
"LABEL_0": 0,
|
158 |
+
"LABEL_1": 1
|
159 |
+
},
|
160 |
+
"length_penalty": 1.0,
|
161 |
+
"max_length": 20,
|
162 |
+
"min_length": 0,
|
163 |
+
"model_type": "",
|
164 |
+
"no_repeat_ngram_size": 0,
|
165 |
+
"num_beam_groups": 1,
|
166 |
+
"num_beams": 1,
|
167 |
+
"num_groups": [
|
168 |
+
8,
|
169 |
+
16,
|
170 |
+
32,
|
171 |
+
64
|
172 |
+
],
|
173 |
+
"num_heads": [
|
174 |
+
8,
|
175 |
+
16,
|
176 |
+
32,
|
177 |
+
64
|
178 |
+
],
|
179 |
+
"num_return_sequences": 1,
|
180 |
+
"output_attentions": false,
|
181 |
+
"output_hidden_states": false,
|
182 |
+
"output_scores": false,
|
183 |
+
"pad_token_id": null,
|
184 |
+
"patch_padding": [
|
185 |
+
3,
|
186 |
+
1,
|
187 |
+
1,
|
188 |
+
1
|
189 |
+
],
|
190 |
+
"patch_prenorm": [
|
191 |
+
false,
|
192 |
+
true,
|
193 |
+
true,
|
194 |
+
true
|
195 |
+
],
|
196 |
+
"patch_size": [
|
197 |
+
7,
|
198 |
+
3,
|
199 |
+
3,
|
200 |
+
3
|
201 |
+
],
|
202 |
+
"patch_stride": [
|
203 |
+
4,
|
204 |
+
2,
|
205 |
+
2,
|
206 |
+
2
|
207 |
+
],
|
208 |
+
"prefix": null,
|
209 |
+
"problem_type": null,
|
210 |
+
"projection_dim": 1024,
|
211 |
+
"pruned_heads": {},
|
212 |
+
"remove_invalid_values": false,
|
213 |
+
"repetition_penalty": 1.0,
|
214 |
+
"return_dict": true,
|
215 |
+
"return_dict_in_generate": false,
|
216 |
+
"sep_token_id": null,
|
217 |
+
"suppress_tokens": null,
|
218 |
+
"task_specific_params": null,
|
219 |
+
"temperature": 1.0,
|
220 |
+
"tf_legacy_loss": false,
|
221 |
+
"tie_encoder_decoder": false,
|
222 |
+
"tie_word_embeddings": true,
|
223 |
+
"tokenizer_class": null,
|
224 |
+
"top_k": 50,
|
225 |
+
"top_p": 1.0,
|
226 |
+
"torch_dtype": null,
|
227 |
+
"torchscript": false,
|
228 |
+
"typical_p": 1.0,
|
229 |
+
"use_bfloat16": false,
|
230 |
+
"visual_temporal_embedding": {
|
231 |
+
"max_temporal_embeddings": 100,
|
232 |
+
"type": "COSINE"
|
233 |
+
},
|
234 |
+
"window_size": 12
|
235 |
+
},
|
236 |
+
"vocab_size": 51289
|
237 |
+
}
|
vision_tower/configuration_florence2.py
ADDED
@@ -0,0 +1,340 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and the HuggingFace Inc. team. All rights reserved.
|
3 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4 |
+
# you may not use this file except in compliance with the License.
|
5 |
+
# You may obtain a copy of the License at
|
6 |
+
#
|
7 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8 |
+
#
|
9 |
+
# Unless required by applicable law or agreed to in writing, software
|
10 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12 |
+
# See the License for the specific language governing permissions and
|
13 |
+
# limitations under the License.
|
14 |
+
import warnings
|
15 |
+
""" Florence-2 configuration"""
|
16 |
+
|
17 |
+
from typing import Optional
|
18 |
+
|
19 |
+
from transformers import AutoConfig
|
20 |
+
from transformers.configuration_utils import PretrainedConfig
|
21 |
+
from transformers.utils import logging
|
22 |
+
|
23 |
+
logger = logging.get_logger(__name__)
|
24 |
+
|
25 |
+
class Florence2VisionConfig(PretrainedConfig):
|
26 |
+
r"""
|
27 |
+
This is the configuration class to store the configuration of a [`Florence2VisionModel`]. It is used to instantiate a Florence2VisionModel
|
28 |
+
according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
29 |
+
defaults will yield a similar configuration to that of the Florence2VisionModel architecture.
|
30 |
+
|
31 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
32 |
+
documentation from [`PretrainedConfig`] for more information.
|
33 |
+
|
34 |
+
Args:
|
35 |
+
drop_path_rate (`float`, *optional*, defaults to 0.1):
|
36 |
+
The dropout rate of the drop path layer.
|
37 |
+
patch_size (`List[int]`, *optional*, defaults to [7, 3, 3, 3]):
|
38 |
+
The patch size of the image.
|
39 |
+
patch_stride (`List[int]`, *optional*, defaults to [4, 2, 2, 2]):
|
40 |
+
The patch stride of the image.
|
41 |
+
patch_padding (`List[int]`, *optional*, defaults to [3, 1, 1, 1]):
|
42 |
+
The patch padding of the image.
|
43 |
+
patch_prenorm (`List[bool]`, *optional*, defaults to [false, true, true, true]):
|
44 |
+
Whether to apply layer normalization before the patch embedding layer.
|
45 |
+
enable_checkpoint (`bool`, *optional*, defaults to False):
|
46 |
+
Whether to enable checkpointing.
|
47 |
+
dim_embed (`List[int]`, *optional*, defaults to [256, 512, 1024, 2048]):
|
48 |
+
The dimension of the embedding layer.
|
49 |
+
num_heads (`List[int]`, *optional*, defaults to [8, 16, 32, 64]):
|
50 |
+
The number of attention heads.
|
51 |
+
num_groups (`List[int]`, *optional*, defaults to [8, 16, 32, 64]):
|
52 |
+
The number of groups.
|
53 |
+
depths (`List[int]`, *optional*, defaults to [1, 1, 9, 1]):
|
54 |
+
The depth of the model.
|
55 |
+
window_size (`int`, *optional*, defaults to 12):
|
56 |
+
The window size of the model.
|
57 |
+
projection_dim (`int`, *optional*, defaults to 1024):
|
58 |
+
The dimension of the projection layer.
|
59 |
+
visual_temporal_embedding (`dict`, *optional*):
|
60 |
+
The configuration of the visual temporal embedding.
|
61 |
+
image_pos_embed (`dict`, *optional*):
|
62 |
+
The configuration of the image position embedding.
|
63 |
+
image_feature_source (`List[str]`, *optional*, defaults to ["spatial_avg_pool", "temporal_avg_pool"]):
|
64 |
+
The source of the image feature.
|
65 |
+
Example:
|
66 |
+
|
67 |
+
```python
|
68 |
+
>>> from transformers import Florence2VisionConfig, Florence2VisionModel
|
69 |
+
|
70 |
+
>>> # Initializing a Florence2 Vision style configuration
|
71 |
+
>>> configuration = Florence2VisionConfig()
|
72 |
+
|
73 |
+
>>> # Initializing a model (with random weights)
|
74 |
+
>>> model = Florence2VisionModel(configuration)
|
75 |
+
|
76 |
+
>>> # Accessing the model configuration
|
77 |
+
>>> configuration = model.config
|
78 |
+
```"""
|
79 |
+
|
80 |
+
model_type = "florence2_vision"
|
81 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
82 |
+
|
83 |
+
def __init__(
|
84 |
+
self,
|
85 |
+
drop_path_rate=0.1,
|
86 |
+
patch_size=[7, 3, 3, 3],
|
87 |
+
patch_stride=[4, 2, 2, 2],
|
88 |
+
patch_padding=[3, 1, 1, 1],
|
89 |
+
patch_prenorm=[False, True, True, True],
|
90 |
+
enable_checkpoint=False,
|
91 |
+
dim_embed=[256, 512, 1024, 2048],
|
92 |
+
num_heads=[8, 16, 32, 64],
|
93 |
+
num_groups=[8, 16, 32, 64],
|
94 |
+
depths=[1, 1, 9, 1],
|
95 |
+
window_size=12,
|
96 |
+
projection_dim=1024,
|
97 |
+
visual_temporal_embedding=None,
|
98 |
+
image_pos_embed=None,
|
99 |
+
image_feature_source=["spatial_avg_pool", "temporal_avg_pool"],
|
100 |
+
**kwargs,
|
101 |
+
):
|
102 |
+
self.drop_path_rate = drop_path_rate
|
103 |
+
self.patch_size = patch_size
|
104 |
+
self.patch_stride = patch_stride
|
105 |
+
self.patch_padding = patch_padding
|
106 |
+
self.patch_prenorm = patch_prenorm
|
107 |
+
self.enable_checkpoint = enable_checkpoint
|
108 |
+
self.dim_embed = dim_embed
|
109 |
+
self.num_heads = num_heads
|
110 |
+
self.num_groups = num_groups
|
111 |
+
self.depths = depths
|
112 |
+
self.window_size = window_size
|
113 |
+
self.projection_dim = projection_dim
|
114 |
+
self.visual_temporal_embedding = visual_temporal_embedding
|
115 |
+
self.image_pos_embed = image_pos_embed
|
116 |
+
self.image_feature_source = image_feature_source
|
117 |
+
|
118 |
+
super().__init__(**kwargs)
|
119 |
+
|
120 |
+
|
121 |
+
|
122 |
+
class Florence2LanguageConfig(PretrainedConfig):
|
123 |
+
r"""
|
124 |
+
This is the configuration class to store the configuration of a [`Florence2LanguagePreTrainedModel`]. It is used to instantiate a BART
|
125 |
+
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
|
126 |
+
defaults will yield a similar configuration to that of the BART
|
127 |
+
[facebook/bart-large](https://huggingface.co/facebook/bart-large) architecture.
|
128 |
+
|
129 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
130 |
+
documentation from [`PretrainedConfig`] for more information.
|
131 |
+
|
132 |
+
|
133 |
+
Args:
|
134 |
+
vocab_size (`int`, *optional*, defaults to 51289):
|
135 |
+
Vocabulary size of the Florence2Language model. Defines the number of different tokens that can be represented by the
|
136 |
+
`inputs_ids` passed when calling [`Florence2LanguageModel`].
|
137 |
+
d_model (`int`, *optional*, defaults to 1024):
|
138 |
+
Dimensionality of the layers and the pooler layer.
|
139 |
+
encoder_layers (`int`, *optional*, defaults to 12):
|
140 |
+
Number of encoder layers.
|
141 |
+
decoder_layers (`int`, *optional*, defaults to 12):
|
142 |
+
Number of decoder layers.
|
143 |
+
encoder_attention_heads (`int`, *optional*, defaults to 16):
|
144 |
+
Number of attention heads for each attention layer in the Transformer encoder.
|
145 |
+
decoder_attention_heads (`int`, *optional*, defaults to 16):
|
146 |
+
Number of attention heads for each attention layer in the Transformer decoder.
|
147 |
+
decoder_ffn_dim (`int`, *optional*, defaults to 4096):
|
148 |
+
Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
|
149 |
+
encoder_ffn_dim (`int`, *optional*, defaults to 4096):
|
150 |
+
Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
|
151 |
+
activation_function (`str` or `function`, *optional*, defaults to `"gelu"`):
|
152 |
+
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
|
153 |
+
`"relu"`, `"silu"` and `"gelu_new"` are supported.
|
154 |
+
dropout (`float`, *optional*, defaults to 0.1):
|
155 |
+
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
|
156 |
+
attention_dropout (`float`, *optional*, defaults to 0.0):
|
157 |
+
The dropout ratio for the attention probabilities.
|
158 |
+
activation_dropout (`float`, *optional*, defaults to 0.0):
|
159 |
+
The dropout ratio for activations inside the fully connected layer.
|
160 |
+
classifier_dropout (`float`, *optional*, defaults to 0.0):
|
161 |
+
The dropout ratio for classifier.
|
162 |
+
max_position_embeddings (`int`, *optional*, defaults to 1024):
|
163 |
+
The maximum sequence length that this model might ever be used with. Typically set this to something large
|
164 |
+
just in case (e.g., 512 or 1024 or 2048).
|
165 |
+
init_std (`float`, *optional*, defaults to 0.02):
|
166 |
+
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
|
167 |
+
encoder_layerdrop (`float`, *optional*, defaults to 0.0):
|
168 |
+
The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
|
169 |
+
for more details.
|
170 |
+
decoder_layerdrop (`float`, *optional*, defaults to 0.0):
|
171 |
+
The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
|
172 |
+
for more details.
|
173 |
+
scale_embedding (`bool`, *optional*, defaults to `False`):
|
174 |
+
Scale embeddings by diving by sqrt(d_model).
|
175 |
+
use_cache (`bool`, *optional*, defaults to `True`):
|
176 |
+
Whether or not the model should return the last key/values attentions (not used by all models).
|
177 |
+
num_labels (`int`, *optional*, defaults to 3):
|
178 |
+
The number of labels to use in [`Florence2LanguageForSequenceClassification`].
|
179 |
+
forced_eos_token_id (`int`, *optional*, defaults to 2):
|
180 |
+
The id of the token to force as the last generated token when `max_length` is reached. Usually set to
|
181 |
+
`eos_token_id`.
|
182 |
+
|
183 |
+
Example:
|
184 |
+
|
185 |
+
```python
|
186 |
+
>>> from transformers import Florence2LanguageConfig, Florence2LanguageModel
|
187 |
+
|
188 |
+
>>> # Initializing a Florence2 Language style configuration
|
189 |
+
>>> configuration = Florence2LanguageConfig()
|
190 |
+
|
191 |
+
>>> # Initializing a model (with random weights)
|
192 |
+
>>> model = Florence2LangaugeModel(configuration)
|
193 |
+
|
194 |
+
>>> # Accessing the model configuration
|
195 |
+
>>> configuration = model.config
|
196 |
+
```"""
|
197 |
+
|
198 |
+
model_type = "florence2_language"
|
199 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
200 |
+
attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}
|
201 |
+
|
202 |
+
def __init__(
|
203 |
+
self,
|
204 |
+
vocab_size=51289,
|
205 |
+
max_position_embeddings=1024,
|
206 |
+
encoder_layers=12,
|
207 |
+
encoder_ffn_dim=4096,
|
208 |
+
encoder_attention_heads=16,
|
209 |
+
decoder_layers=12,
|
210 |
+
decoder_ffn_dim=4096,
|
211 |
+
decoder_attention_heads=16,
|
212 |
+
encoder_layerdrop=0.0,
|
213 |
+
decoder_layerdrop=0.0,
|
214 |
+
activation_function="gelu",
|
215 |
+
d_model=1024,
|
216 |
+
dropout=0.1,
|
217 |
+
attention_dropout=0.0,
|
218 |
+
activation_dropout=0.0,
|
219 |
+
init_std=0.02,
|
220 |
+
classifier_dropout=0.0,
|
221 |
+
scale_embedding=False,
|
222 |
+
use_cache=True,
|
223 |
+
num_labels=3,
|
224 |
+
pad_token_id=1,
|
225 |
+
bos_token_id=0,
|
226 |
+
eos_token_id=2,
|
227 |
+
is_encoder_decoder=True,
|
228 |
+
decoder_start_token_id=2,
|
229 |
+
forced_eos_token_id=2,
|
230 |
+
**kwargs,
|
231 |
+
):
|
232 |
+
self.vocab_size = vocab_size
|
233 |
+
self.max_position_embeddings = max_position_embeddings
|
234 |
+
self.d_model = d_model
|
235 |
+
self.encoder_ffn_dim = encoder_ffn_dim
|
236 |
+
self.encoder_layers = encoder_layers
|
237 |
+
self.encoder_attention_heads = encoder_attention_heads
|
238 |
+
self.decoder_ffn_dim = decoder_ffn_dim
|
239 |
+
self.decoder_layers = decoder_layers
|
240 |
+
self.decoder_attention_heads = decoder_attention_heads
|
241 |
+
self.dropout = dropout
|
242 |
+
self.attention_dropout = attention_dropout
|
243 |
+
self.activation_dropout = activation_dropout
|
244 |
+
self.activation_function = activation_function
|
245 |
+
self.init_std = init_std
|
246 |
+
self.encoder_layerdrop = encoder_layerdrop
|
247 |
+
self.decoder_layerdrop = decoder_layerdrop
|
248 |
+
self.classifier_dropout = classifier_dropout
|
249 |
+
self.use_cache = use_cache
|
250 |
+
self.num_hidden_layers = encoder_layers
|
251 |
+
self.scale_embedding = scale_embedding # scale factor will be sqrt(d_model) if True
|
252 |
+
|
253 |
+
super().__init__(
|
254 |
+
num_labels=num_labels,
|
255 |
+
pad_token_id=pad_token_id,
|
256 |
+
bos_token_id=bos_token_id,
|
257 |
+
eos_token_id=eos_token_id,
|
258 |
+
is_encoder_decoder=is_encoder_decoder,
|
259 |
+
decoder_start_token_id=decoder_start_token_id,
|
260 |
+
forced_eos_token_id=forced_eos_token_id,
|
261 |
+
**kwargs,
|
262 |
+
)
|
263 |
+
|
264 |
+
# ensure backward compatibility for BART CNN models
|
265 |
+
if self.forced_bos_token_id is None and kwargs.get("force_bos_token_to_be_generated", False):
|
266 |
+
self.forced_bos_token_id = self.bos_token_id
|
267 |
+
warnings.warn(
|
268 |
+
f"Please make sure the config includes `forced_bos_token_id={self.bos_token_id}` in future versions. "
|
269 |
+
"The config can simply be saved and uploaded again to be fixed."
|
270 |
+
)
|
271 |
+
|
272 |
+
class Florence2Config(PretrainedConfig):
|
273 |
+
r"""
|
274 |
+
This is the configuration class to store the configuration of a [`Florence2ForConditionalGeneration`]. It is used to instantiate an
|
275 |
+
Florence-2 model according to the specified arguments, defining the model architecture.
|
276 |
+
|
277 |
+
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
|
278 |
+
documentation from [`PretrainedConfig`] for more information.
|
279 |
+
|
280 |
+
Args:
|
281 |
+
vision_config (`Florence2VisionConfig`, *optional*):
|
282 |
+
Custom vision config or dict
|
283 |
+
text_config (`Union[AutoConfig, dict]`, *optional*):
|
284 |
+
The config object of the text backbone.
|
285 |
+
ignore_index (`int`, *optional*, defaults to -100):
|
286 |
+
The ignore index for the loss function.
|
287 |
+
vocab_size (`int`, *optional*, defaults to 51289):
|
288 |
+
Vocabulary size of the Florence2model. Defines the number of different tokens that can be represented by the
|
289 |
+
`inputs_ids` passed when calling [`~Florence2ForConditionalGeneration`]
|
290 |
+
projection_dim (`int`, *optional*, defaults to 1024):
|
291 |
+
Dimension of the multimodal projection space.
|
292 |
+
|
293 |
+
Example:
|
294 |
+
|
295 |
+
```python
|
296 |
+
>>> from transformers import Florence2ForConditionalGeneration, Florence2Config, CLIPVisionConfig, BartConfig
|
297 |
+
|
298 |
+
>>> # Initializing a clip-like vision config
|
299 |
+
>>> vision_config = CLIPVisionConfig()
|
300 |
+
|
301 |
+
>>> # Initializing a Bart config
|
302 |
+
>>> text_config = BartConfig()
|
303 |
+
|
304 |
+
>>> # Initializing a Florence-2 configuration
|
305 |
+
>>> configuration = Florence2Config(vision_config, text_config)
|
306 |
+
|
307 |
+
>>> # Initializing a model from the florence-2 configuration
|
308 |
+
>>> model = Florence2ForConditionalGeneration(configuration)
|
309 |
+
|
310 |
+
>>> # Accessing the model configuration
|
311 |
+
>>> configuration = model.config
|
312 |
+
```"""
|
313 |
+
|
314 |
+
model_type = "florence2"
|
315 |
+
is_composition = False
|
316 |
+
|
317 |
+
def __init__(
|
318 |
+
self,
|
319 |
+
vision_config=None,
|
320 |
+
text_config=None,
|
321 |
+
ignore_index=-100,
|
322 |
+
vocab_size=51289,
|
323 |
+
projection_dim=1024,
|
324 |
+
**kwargs,
|
325 |
+
):
|
326 |
+
self.ignore_index = ignore_index
|
327 |
+
self.vocab_size = vocab_size
|
328 |
+
self.projection_dim = projection_dim
|
329 |
+
if vision_config is not None:
|
330 |
+
vision_config = PretrainedConfig(**vision_config)
|
331 |
+
self.vision_config = vision_config
|
332 |
+
self.vocab_size = self.vocab_size
|
333 |
+
|
334 |
+
self.text_config = text_config
|
335 |
+
if text_config is not None:
|
336 |
+
self.text_config = Florence2LanguageConfig(**text_config)
|
337 |
+
|
338 |
+
|
339 |
+
super().__init__(**kwargs)
|
340 |
+
|
vision_tower/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vision_tower/modeling_florence2.py
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vision_tower/preprocessor_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoProcessor": "processing_florence2.Florence2Processor"
|
4 |
+
},
|
5 |
+
"crop_size": {
|
6 |
+
"height": 768,
|
7 |
+
"width": 768
|
8 |
+
},
|
9 |
+
"do_center_crop": false,
|
10 |
+
"do_convert_rgb": null,
|
11 |
+
"do_normalize": true,
|
12 |
+
"do_rescale": true,
|
13 |
+
"do_resize": true,
|
14 |
+
"image_mean": [
|
15 |
+
0.485,
|
16 |
+
0.456,
|
17 |
+
0.406
|
18 |
+
],
|
19 |
+
"image_processor_type": "CLIPImageProcessor",
|
20 |
+
"image_seq_length": 577,
|
21 |
+
"image_std": [
|
22 |
+
0.229,
|
23 |
+
0.224,
|
24 |
+
0.225
|
25 |
+
],
|
26 |
+
"processor_class": "Florence2Processor",
|
27 |
+
"resample": 3,
|
28 |
+
"rescale_factor": 0.00392156862745098,
|
29 |
+
"size": {
|
30 |
+
"height": 768,
|
31 |
+
"width": 768
|
32 |
+
}
|
33 |
+
}
|
vision_tower/processing_florence2.py
ADDED
@@ -0,0 +1,1124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# coding=utf-8
|
2 |
+
# Copyright 2024 Microsoft and The HuggingFace Inc. team.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
"""
|
16 |
+
Processor class for Florence-2.
|
17 |
+
"""
|
18 |
+
|
19 |
+
import re
|
20 |
+
import logging
|
21 |
+
from typing import List, Optional, Union
|
22 |
+
import numpy as np
|
23 |
+
|
24 |
+
import torch
|
25 |
+
|
26 |
+
from transformers.feature_extraction_utils import BatchFeature
|
27 |
+
from transformers.image_utils import ImageInput, is_valid_image
|
28 |
+
from transformers.processing_utils import ProcessorMixin
|
29 |
+
from transformers.tokenization_utils_base import (
|
30 |
+
PaddingStrategy,
|
31 |
+
PreTokenizedInput,
|
32 |
+
TextInput,
|
33 |
+
TruncationStrategy,
|
34 |
+
)
|
35 |
+
from transformers.utils import TensorType
|
36 |
+
|
37 |
+
|
38 |
+
logger = logging.getLogger(__name__)
|
39 |
+
|
40 |
+
# Copied from transformers.models.idefics2.processing_idefics2.is_url
|
41 |
+
def is_url(val) -> bool:
|
42 |
+
return isinstance(val, str) and val.startswith("http")
|
43 |
+
|
44 |
+
# Copied from transformers.models.idefics2.processing_idefics2.is_image_or_image_url
|
45 |
+
def is_image_or_image_url(elem):
|
46 |
+
return is_url(elem) or is_valid_image(elem)
|
47 |
+
|
48 |
+
|
49 |
+
def _is_str_or_image(elem):
|
50 |
+
return isinstance(elem, (str)) or is_image_or_image_url(elem)
|
51 |
+
|
52 |
+
|
53 |
+
class Florence2Processor(ProcessorMixin):
|
54 |
+
r"""
|
55 |
+
Constructs a Florence2 processor which wraps a Florence2 image processor and a Florence2 tokenizer into a single processor.
|
56 |
+
|
57 |
+
[`Florence2Processor`] offers all the functionalities of [`CLIPImageProcessor`] and [`BartTokenizerFast`]. See the
|
58 |
+
[`~Florence2Processor.__call__`] and [`~Florence2Processor.decode`] for more information.
|
59 |
+
|
60 |
+
Args:
|
61 |
+
image_processor ([`CLIPImageProcessor`], *optional*):
|
62 |
+
The image processor is a required input.
|
63 |
+
tokenizer ([`BartTokenizerFast`], *optional*):
|
64 |
+
The tokenizer is a required input.
|
65 |
+
"""
|
66 |
+
|
67 |
+
attributes = ["image_processor", "tokenizer"]
|
68 |
+
image_processor_class = "CLIPImageProcessor"
|
69 |
+
tokenizer_class = ("BartTokenizer", "BartTokenizerFast")
|
70 |
+
|
71 |
+
def __init__(
|
72 |
+
self,
|
73 |
+
image_processor=None,
|
74 |
+
tokenizer=None,
|
75 |
+
):
|
76 |
+
if image_processor is None:
|
77 |
+
raise ValueError("You need to specify an `image_processor`.")
|
78 |
+
if tokenizer is None:
|
79 |
+
raise ValueError("You need to specify a `tokenizer`.")
|
80 |
+
if not hasattr(image_processor, "image_seq_length"):
|
81 |
+
raise ValueError("Image processor is missing an `image_seq_length` attribute.")
|
82 |
+
|
83 |
+
self.image_seq_length = image_processor.image_seq_length
|
84 |
+
|
85 |
+
tokens_to_add = {
|
86 |
+
'additional_special_tokens': \
|
87 |
+
tokenizer.additional_special_tokens + \
|
88 |
+
['<od>', '</od>', '<ocr>', '</ocr>'] + \
|
89 |
+
[f'<loc_{x}>' for x in range(1000)] + \
|
90 |
+
['<cap>', '</cap>', '<ncap>', '</ncap>','<dcap>', '</dcap>', '<grounding>', '</grounding>', '<seg>', '</seg>', '<sep>', '<region_cap>', '</region_cap>', '<region_to_desciption>', '</region_to_desciption>', '<proposal>', '</proposal>', '<poly>', '</poly>', '<and>']
|
91 |
+
}
|
92 |
+
tokenizer.add_special_tokens(tokens_to_add)
|
93 |
+
|
94 |
+
self.tasks_answer_post_processing_type = {
|
95 |
+
'<OCR>': 'pure_text',
|
96 |
+
'<OCR_WITH_REGION>': 'ocr',
|
97 |
+
'<CAPTION>': 'pure_text',
|
98 |
+
'<DETAILED_CAPTION>': 'pure_text',
|
99 |
+
'<MORE_DETAILED_CAPTION>': 'pure_text',
|
100 |
+
'<OD>': 'description_with_bboxes',
|
101 |
+
'<DENSE_REGION_CAPTION>': 'description_with_bboxes',
|
102 |
+
'<CAPTION_TO_PHRASE_GROUNDING>': "phrase_grounding",
|
103 |
+
'<REFERRING_EXPRESSION_SEGMENTATION>': 'polygons',
|
104 |
+
'<REGION_TO_SEGMENTATION>': 'polygons',
|
105 |
+
'<OPEN_VOCABULARY_DETECTION>': 'description_with_bboxes_or_polygons',
|
106 |
+
'<REGION_TO_CATEGORY>': 'pure_text',
|
107 |
+
'<REGION_TO_DESCRIPTION>': 'pure_text',
|
108 |
+
'<REGION_TO_OCR>': 'pure_text',
|
109 |
+
'<REGION_PROPOSAL>': 'bboxes'
|
110 |
+
}
|
111 |
+
|
112 |
+
self.task_prompts_without_inputs = {
|
113 |
+
'<OCR>': 'What is the text in the image?',
|
114 |
+
'<OCR_WITH_REGION>': 'What is the text in the image, with regions?',
|
115 |
+
'<CAPTION>': 'What does the image describe?',
|
116 |
+
'<DETAILED_CAPTION>': 'Describe in detail what is shown in the image.',
|
117 |
+
'<MORE_DETAILED_CAPTION>': 'Describe with a paragraph what is shown in the image.',
|
118 |
+
'<OD>': 'Locate the objects with category name in the image.',
|
119 |
+
'<DENSE_REGION_CAPTION>': 'Locate the objects in the image, with their descriptions.',
|
120 |
+
'<REGION_PROPOSAL>': 'Locate the region proposals in the image.'
|
121 |
+
}
|
122 |
+
|
123 |
+
self.task_prompts_with_input = {
|
124 |
+
'<CAPTION_TO_PHRASE_GROUNDING>': "Locate the phrases in the caption: {input}",
|
125 |
+
'<REFERRING_EXPRESSION_SEGMENTATION>': 'Locate {input} in the image with mask',
|
126 |
+
'<REGION_TO_SEGMENTATION>': 'What is the polygon mask of region {input}',
|
127 |
+
'<OPEN_VOCABULARY_DETECTION>': 'Locate {input} in the image.',
|
128 |
+
'<REGION_TO_CATEGORY>': 'What is the region {input}?',
|
129 |
+
'<REGION_TO_DESCRIPTION>': 'What does the region {input} describe?',
|
130 |
+
'<REGION_TO_OCR>': 'What text is in the region {input}?',
|
131 |
+
}
|
132 |
+
self.image_mean = image_processor.image_mean
|
133 |
+
self.image_std = image_processor.image_std
|
134 |
+
self.crop_size = image_processor.crop_size
|
135 |
+
self.post_processor = Florence2PostProcesser(tokenizer=tokenizer)
|
136 |
+
|
137 |
+
|
138 |
+
super().__init__(image_processor, tokenizer)
|
139 |
+
|
140 |
+
def _construct_prompts(self, text):
|
141 |
+
# replace the task tokens with the task prompts if task token is in the text
|
142 |
+
prompts = []
|
143 |
+
for _text in text:
|
144 |
+
# 1. fixed task prompts without additional inputs
|
145 |
+
for task_token, task_prompt in self.task_prompts_without_inputs.items():
|
146 |
+
if task_token in _text:
|
147 |
+
assert _text == task_token, f"Task token {task_token} should be the only token in the text."
|
148 |
+
_text = task_prompt
|
149 |
+
break
|
150 |
+
# 2. task prompts with additional inputs
|
151 |
+
for task_token, task_prompt in self.task_prompts_with_input.items():
|
152 |
+
if task_token in _text:
|
153 |
+
_text = task_prompt.format(input=_text.replace(task_token, ''))
|
154 |
+
break
|
155 |
+
prompts.append(_text)
|
156 |
+
return prompts
|
157 |
+
|
158 |
+
def __call__(
|
159 |
+
self,
|
160 |
+
text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
|
161 |
+
images: ImageInput = None,
|
162 |
+
tokenize_newline_separately: bool = True,
|
163 |
+
padding: Union[bool, str, PaddingStrategy] = False,
|
164 |
+
truncation: Union[bool, str, TruncationStrategy] = None,
|
165 |
+
max_length=None,
|
166 |
+
return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
|
167 |
+
do_resize: bool = None,
|
168 |
+
do_normalize: bool = None,
|
169 |
+
image_mean: Optional[Union[float, List[float]]] = None,
|
170 |
+
image_std: Optional[Union[float, List[float]]] = None,
|
171 |
+
data_format: Optional["ChannelDimension"] = "channels_first", # noqa: F821
|
172 |
+
input_data_format: Optional[
|
173 |
+
Union[str, "ChannelDimension"] # noqa: F821
|
174 |
+
] = None,
|
175 |
+
resample: "PILImageResampling" = None, # noqa: F821
|
176 |
+
do_convert_rgb: bool = None,
|
177 |
+
do_thumbnail: bool = None,
|
178 |
+
do_align_long_axis: bool = None,
|
179 |
+
do_rescale: bool = None,
|
180 |
+
) -> BatchFeature:
|
181 |
+
"""
|
182 |
+
Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
|
183 |
+
and `kwargs` arguments to BartTokenizerFast's [`~BartTokenizerFast.__call__`] if `text` is not `None` to encode
|
184 |
+
the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
|
185 |
+
CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
|
186 |
+
of the above two methods for more information.
|
187 |
+
|
188 |
+
Args:
|
189 |
+
text (`str`, `List[str]`, `List[List[str]]`):
|
190 |
+
The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
|
191 |
+
(pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
|
192 |
+
`is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
|
193 |
+
images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
|
194 |
+
The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
|
195 |
+
tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a
|
196 |
+
number of channels, H and W are image height and width.
|
197 |
+
tokenize_newline_separately (`bool`, defaults to `True`):
|
198 |
+
Adds a separately tokenized '\n' at the end of the prompt.
|
199 |
+
padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
|
200 |
+
Select a strategy to pad the returned sequences (according to the model's padding side and padding
|
201 |
+
index) among:
|
202 |
+
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
|
203 |
+
sequence if provided).
|
204 |
+
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
|
205 |
+
acceptable input length for the model if that argument is not provided.
|
206 |
+
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
|
207 |
+
lengths).
|
208 |
+
max_length (`int`, *optional*):
|
209 |
+
Maximum length of the returned list and optionally padding length (see above).
|
210 |
+
truncation (`bool`, *optional*):
|
211 |
+
Activates truncation to cut input sequences longer than `max_length` to `max_length`.
|
212 |
+
return_tensors (`str` or [`~utils.TensorType`], *optional*):
|
213 |
+
If set, will return tensors of a particular framework. Acceptable values are:
|
214 |
+
|
215 |
+
- `'tf'`: Return TensorFlow `tf.constant` objects.
|
216 |
+
- `'pt'`: Return PyTorch `torch.Tensor` objects.
|
217 |
+
- `'np'`: Return NumPy `np.ndarray` objects.
|
218 |
+
- `'jax'`: Return JAX `jnp.ndarray` objects.
|
219 |
+
|
220 |
+
Returns:
|
221 |
+
[`BatchFeature`]: A [`BatchFeature`] with the following fields:
|
222 |
+
|
223 |
+
- **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. If `suffix`
|
224 |
+
is provided, the `input_ids` will also contain the suffix input ids.
|
225 |
+
- **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
|
226 |
+
`return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
|
227 |
+
`None`).
|
228 |
+
- **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
|
229 |
+
- **labels** -- Labels compatible with training if `suffix` is not None
|
230 |
+
"""
|
231 |
+
|
232 |
+
return_token_type_ids = False
|
233 |
+
|
234 |
+
if images is None:
|
235 |
+
raise ValueError("`images` are expected as arguments to a `Florence2Processor` instance.")
|
236 |
+
if text is None:
|
237 |
+
logger.warning_once(
|
238 |
+
"You are using Florence-2 without a text prompt."
|
239 |
+
)
|
240 |
+
text = ""
|
241 |
+
|
242 |
+
if isinstance(text, List) and isinstance(images, List):
|
243 |
+
if len(images) < len(text):
|
244 |
+
raise ValueError(
|
245 |
+
f"Received {len(images)} images for {len(text)} prompts. Each prompt should be associated with an image."
|
246 |
+
)
|
247 |
+
if _is_str_or_image(text):
|
248 |
+
text = [text]
|
249 |
+
elif isinstance(text, list) and _is_str_or_image(text[0]):
|
250 |
+
pass
|
251 |
+
|
252 |
+
try:
|
253 |
+
pixel_values = self.image_processor(
|
254 |
+
images,
|
255 |
+
do_resize=do_resize,
|
256 |
+
do_normalize=do_normalize,
|
257 |
+
return_tensors=return_tensors,
|
258 |
+
image_mean=image_mean,
|
259 |
+
image_std=image_std,
|
260 |
+
input_data_format=input_data_format,
|
261 |
+
data_format=data_format,
|
262 |
+
resample=resample,
|
263 |
+
do_convert_rgb=do_convert_rgb,
|
264 |
+
)["pixel_values"]
|
265 |
+
except ValueError as e:
|
266 |
+
try:
|
267 |
+
pixel_values = self.image_processor(
|
268 |
+
images,
|
269 |
+
do_resize=do_resize,
|
270 |
+
do_normalize=do_normalize,
|
271 |
+
return_tensors=return_tensors,
|
272 |
+
image_mean=image_mean[1],
|
273 |
+
image_std=image_std[1],
|
274 |
+
input_data_format=input_data_format,
|
275 |
+
data_format=data_format,
|
276 |
+
resample=resample,
|
277 |
+
do_convert_rgb=do_convert_rgb,
|
278 |
+
)["pixel_values"]
|
279 |
+
print("Grayscale processing succeeded")
|
280 |
+
except ValueError as e:
|
281 |
+
print(f"Grayscale processing failed: {e}")
|
282 |
+
|
283 |
+
|
284 |
+
|
285 |
+
# pixel_values = self.image_processor(
|
286 |
+
# images,
|
287 |
+
# do_resize=do_resize,
|
288 |
+
# do_normalize=do_normalize,
|
289 |
+
# return_tensors=return_tensors,
|
290 |
+
# image_mean=image_mean,
|
291 |
+
# image_std=image_std,
|
292 |
+
# input_data_format=input_data_format,
|
293 |
+
# data_format=data_format,
|
294 |
+
# resample=resample,
|
295 |
+
# do_convert_rgb=do_convert_rgb,
|
296 |
+
# )["pixel_values"]
|
297 |
+
|
298 |
+
|
299 |
+
if max_length is not None:
|
300 |
+
max_length -= self.image_seq_length # max_length has to account for the image tokens
|
301 |
+
|
302 |
+
text = self._construct_prompts(text)
|
303 |
+
|
304 |
+
inputs = self.tokenizer(
|
305 |
+
text,
|
306 |
+
return_tensors=return_tensors,
|
307 |
+
padding=padding,
|
308 |
+
max_length=max_length,
|
309 |
+
truncation=truncation,
|
310 |
+
return_token_type_ids=return_token_type_ids,
|
311 |
+
)
|
312 |
+
|
313 |
+
return_data = {**inputs, "pixel_values": pixel_values}
|
314 |
+
|
315 |
+
if return_token_type_ids:
|
316 |
+
labels = inputs["input_ids"].masked_fill(inputs["token_type_ids"] == 0, -100)
|
317 |
+
return_data.update({"labels": labels})
|
318 |
+
return BatchFeature(data=return_data)
|
319 |
+
|
320 |
+
# Copied from transformers.models.clip.processing_clip.CLIPProcessor.batch_decode with CLIP->Florence2
|
321 |
+
def batch_decode(self, *args, **kwargs):
|
322 |
+
"""
|
323 |
+
This method forwards all its arguments to BartTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
|
324 |
+
refer to the docstring of this method for more information.
|
325 |
+
"""
|
326 |
+
return self.tokenizer.batch_decode(*args, **kwargs)
|
327 |
+
|
328 |
+
# Copied from transformers.models.clip.processing_clip.CLIPProcessor.decode with CLIP->Florence2
|
329 |
+
def decode(self, *args, **kwargs):
|
330 |
+
"""
|
331 |
+
This method forwards all its arguments to BartTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
|
332 |
+
the docstring of this method for more information.
|
333 |
+
"""
|
334 |
+
return self.tokenizer.decode(*args, **kwargs)
|
335 |
+
|
336 |
+
@property
|
337 |
+
# Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names with CLIP->Florence2
|
338 |
+
def model_input_names(self):
|
339 |
+
tokenizer_input_names = self.tokenizer.model_input_names
|
340 |
+
image_processor_input_names = self.image_processor.model_input_names
|
341 |
+
return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))
|
342 |
+
|
343 |
+
def post_process_generation(self, text, task, image_size):
|
344 |
+
"""
|
345 |
+
Post-process the output of the model to each of the task outputs.
|
346 |
+
|
347 |
+
Args:
|
348 |
+
text (`str`): The text to post-process.
|
349 |
+
task (`str`): The task to post-process the text for.
|
350 |
+
image_size (`Tuple[int, int]`): The size of the image. height x width.
|
351 |
+
"""
|
352 |
+
|
353 |
+
task_answer_post_processing_type = self.tasks_answer_post_processing_type.get(task, 'pure_text')
|
354 |
+
task_answer = self.post_processor(
|
355 |
+
text=text,
|
356 |
+
image_size=image_size,
|
357 |
+
parse_tasks=task_answer_post_processing_type,
|
358 |
+
)[task_answer_post_processing_type]
|
359 |
+
|
360 |
+
if task_answer_post_processing_type == 'pure_text':
|
361 |
+
final_answer = task_answer
|
362 |
+
# remove the special tokens
|
363 |
+
final_answer = final_answer.replace('<s>', '').replace('</s>', '')
|
364 |
+
elif task_answer_post_processing_type in ['od', 'description_with_bboxes', 'bboxes']:
|
365 |
+
od_instances = task_answer
|
366 |
+
bboxes_od = [_od_instance['bbox'] for _od_instance in od_instances]
|
367 |
+
labels_od = [str(_od_instance['cat_name']) for _od_instance in od_instances]
|
368 |
+
final_answer = {'bboxes': bboxes_od, 'labels': labels_od}
|
369 |
+
elif task_answer_post_processing_type in ['ocr']:
|
370 |
+
bboxes = [_od_instance['quad_box'] for _od_instance in task_answer]
|
371 |
+
labels = [str(_od_instance['text']) for _od_instance in task_answer]
|
372 |
+
final_answer = {'quad_boxes': bboxes, 'labels': labels}
|
373 |
+
elif task_answer_post_processing_type in ['phrase_grounding']:
|
374 |
+
bboxes = []
|
375 |
+
labels = []
|
376 |
+
for _grounded_phrase in task_answer:
|
377 |
+
for _bbox in _grounded_phrase['bbox']:
|
378 |
+
bboxes.append(_bbox)
|
379 |
+
labels.append(_grounded_phrase['cat_name'])
|
380 |
+
final_answer = {'bboxes': bboxes, 'labels': labels}
|
381 |
+
elif task_answer_post_processing_type in ['description_with_polygons', 'polygons']:
|
382 |
+
labels = []
|
383 |
+
polygons = []
|
384 |
+
for result in task_answer:
|
385 |
+
label = result['cat_name']
|
386 |
+
_polygons = result['polygons']
|
387 |
+
labels.append(label)
|
388 |
+
polygons.append(_polygons)
|
389 |
+
final_answer = {'polygons': polygons, 'labels': labels}
|
390 |
+
elif task_answer_post_processing_type in ['description_with_bboxes_or_polygons']:
|
391 |
+
bboxes = []
|
392 |
+
bboxes_labels = []
|
393 |
+
polygons = []
|
394 |
+
polygons_labels = []
|
395 |
+
for result in task_answer:
|
396 |
+
label = result['cat_name']
|
397 |
+
if 'polygons' in result:
|
398 |
+
_polygons = result['polygons']
|
399 |
+
polygons.append(_polygons)
|
400 |
+
polygons_labels.append(label)
|
401 |
+
else:
|
402 |
+
_bbox = result['bbox']
|
403 |
+
bboxes.append(_bbox)
|
404 |
+
bboxes_labels.append(label)
|
405 |
+
final_answer = {'bboxes': bboxes, 'bboxes_labels': bboxes_labels, 'polygons': polygons, 'polygons_labels': polygons_labels}
|
406 |
+
else:
|
407 |
+
raise ValueError('Unknown task answer post processing type: {}'.format(task_answer_post_processing_type))
|
408 |
+
|
409 |
+
final_answer = {
|
410 |
+
task: final_answer}
|
411 |
+
return final_answer
|
412 |
+
|
413 |
+
class BoxQuantizer(object):
|
414 |
+
def __init__(self, mode, bins):
|
415 |
+
self.mode = mode
|
416 |
+
self.bins = bins
|
417 |
+
|
418 |
+
def quantize(self, boxes: torch.Tensor, size):
|
419 |
+
bins_w, bins_h = self.bins # Quantization bins.
|
420 |
+
size_w, size_h = size # Original image size.
|
421 |
+
size_per_bin_w = size_w / bins_w
|
422 |
+
size_per_bin_h = size_h / bins_h
|
423 |
+
xmin, ymin, xmax, ymax = boxes.split(1, dim=-1) # Shape: 4 * [N, 1].
|
424 |
+
|
425 |
+
if self.mode == 'floor':
|
426 |
+
quantized_xmin = (
|
427 |
+
xmin / size_per_bin_w).floor().clamp(0, bins_w - 1)
|
428 |
+
quantized_ymin = (
|
429 |
+
ymin / size_per_bin_h).floor().clamp(0, bins_h - 1)
|
430 |
+
quantized_xmax = (
|
431 |
+
xmax / size_per_bin_w).floor().clamp(0, bins_w - 1)
|
432 |
+
quantized_ymax = (
|
433 |
+
ymax / size_per_bin_h).floor().clamp(0, bins_h - 1)
|
434 |
+
|
435 |
+
elif self.mode == 'round':
|
436 |
+
raise NotImplementedError()
|
437 |
+
|
438 |
+
else:
|
439 |
+
raise ValueError('Incorrect quantization type.')
|
440 |
+
|
441 |
+
quantized_boxes = torch.cat(
|
442 |
+
(quantized_xmin, quantized_ymin, quantized_xmax, quantized_ymax), dim=-1
|
443 |
+
).int()
|
444 |
+
|
445 |
+
return quantized_boxes
|
446 |
+
|
447 |
+
def dequantize(self, boxes: torch.Tensor, size):
|
448 |
+
bins_w, bins_h = self.bins # Quantization bins.
|
449 |
+
size_w, size_h = size # Original image size.
|
450 |
+
size_per_bin_w = size_w / bins_w
|
451 |
+
size_per_bin_h = size_h / bins_h
|
452 |
+
xmin, ymin, xmax, ymax = boxes.split(1, dim=-1) # Shape: 4 * [N, 1].
|
453 |
+
|
454 |
+
if self.mode == 'floor':
|
455 |
+
# Add 0.5 to use the center position of the bin as the coordinate.
|
456 |
+
dequantized_xmin = (xmin + 0.5) * size_per_bin_w
|
457 |
+
dequantized_ymin = (ymin + 0.5) * size_per_bin_h
|
458 |
+
dequantized_xmax = (xmax + 0.5) * size_per_bin_w
|
459 |
+
dequantized_ymax = (ymax + 0.5) * size_per_bin_h
|
460 |
+
|
461 |
+
elif self.mode == 'round':
|
462 |
+
raise NotImplementedError()
|
463 |
+
|
464 |
+
else:
|
465 |
+
raise ValueError('Incorrect quantization type.')
|
466 |
+
|
467 |
+
dequantized_boxes = torch.cat(
|
468 |
+
(dequantized_xmin, dequantized_ymin,
|
469 |
+
dequantized_xmax, dequantized_ymax), dim=-1
|
470 |
+
)
|
471 |
+
|
472 |
+
return dequantized_boxes
|
473 |
+
|
474 |
+
|
475 |
+
class CoordinatesQuantizer(object):
|
476 |
+
"""
|
477 |
+
Quantize coornidates (Nx2)
|
478 |
+
"""
|
479 |
+
|
480 |
+
def __init__(self, mode, bins):
|
481 |
+
self.mode = mode
|
482 |
+
self.bins = bins
|
483 |
+
|
484 |
+
def quantize(self, coordinates: torch.Tensor, size):
|
485 |
+
bins_w, bins_h = self.bins # Quantization bins.
|
486 |
+
size_w, size_h = size # Original image size.
|
487 |
+
size_per_bin_w = size_w / bins_w
|
488 |
+
size_per_bin_h = size_h / bins_h
|
489 |
+
assert coordinates.shape[-1] == 2, 'coordinates should be shape (N, 2)'
|
490 |
+
x, y = coordinates.split(1, dim=-1) # Shape: 4 * [N, 1].
|
491 |
+
|
492 |
+
if self.mode == 'floor':
|
493 |
+
quantized_x = (x / size_per_bin_w).floor().clamp(0, bins_w - 1)
|
494 |
+
quantized_y = (y / size_per_bin_h).floor().clamp(0, bins_h - 1)
|
495 |
+
|
496 |
+
elif self.mode == 'round':
|
497 |
+
raise NotImplementedError()
|
498 |
+
|
499 |
+
else:
|
500 |
+
raise ValueError('Incorrect quantization type.')
|
501 |
+
|
502 |
+
quantized_coordinates = torch.cat(
|
503 |
+
(quantized_x, quantized_y), dim=-1
|
504 |
+
).int()
|
505 |
+
|
506 |
+
return quantized_coordinates
|
507 |
+
|
508 |
+
def dequantize(self, coordinates: torch.Tensor, size):
|
509 |
+
bins_w, bins_h = self.bins # Quantization bins.
|
510 |
+
size_w, size_h = size # Original image size.
|
511 |
+
size_per_bin_w = size_w / bins_w
|
512 |
+
size_per_bin_h = size_h / bins_h
|
513 |
+
assert coordinates.shape[-1] == 2, 'coordinates should be shape (N, 2)'
|
514 |
+
x, y = coordinates.split(1, dim=-1) # Shape: 4 * [N, 1].
|
515 |
+
|
516 |
+
if self.mode == 'floor':
|
517 |
+
# Add 0.5 to use the center position of the bin as the coordinate.
|
518 |
+
dequantized_x = (x + 0.5) * size_per_bin_w
|
519 |
+
dequantized_y = (y + 0.5) * size_per_bin_h
|
520 |
+
|
521 |
+
elif self.mode == 'round':
|
522 |
+
raise NotImplementedError()
|
523 |
+
|
524 |
+
else:
|
525 |
+
raise ValueError('Incorrect quantization type.')
|
526 |
+
|
527 |
+
dequantized_coordinates = torch.cat(
|
528 |
+
(dequantized_x, dequantized_y), dim=-1
|
529 |
+
)
|
530 |
+
|
531 |
+
return dequantized_coordinates
|
532 |
+
|
533 |
+
|
534 |
+
class Florence2PostProcesser(object):
|
535 |
+
"""
|
536 |
+
Florence-2 post process for converting text prediction to various tasks results.
|
537 |
+
|
538 |
+
Args:
|
539 |
+
config: A dict of configs.
|
540 |
+
tokenizer: A tokenizer for decoding text to spans.
|
541 |
+
sample config:
|
542 |
+
UNIFIED_POST_PROCESS:
|
543 |
+
# commom configs
|
544 |
+
NUM_BBOX_HEIGHT_BINS: 1000
|
545 |
+
NUM_BBOX_WIDTH_BINS: 1000
|
546 |
+
COORDINATES_HEIGHT_BINS: 1000
|
547 |
+
COORDINATES_WIDTH_BINS: 1000
|
548 |
+
# task specific configs, override the common configs
|
549 |
+
PRASE_TASKS:
|
550 |
+
- TASK_NAME: 'video_dense_caption'
|
551 |
+
PATTERN: 'r<time_(\d+)><time_(\d+)>([a-zA-Z0-9 ]+)'
|
552 |
+
SCORE_MODE: 'avg_cat_name_scores'
|
553 |
+
NUM_BINS: 100
|
554 |
+
- TASK_NAME: 'od'
|
555 |
+
PATTERN: 'r<loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)>([a-zA-Z0-9 ]+)'
|
556 |
+
SCORE_MODE: 'avg_cat_name_scores'
|
557 |
+
|
558 |
+
Returns:
|
559 |
+
parsed_dict (dict): A dict of parsed results.
|
560 |
+
"""
|
561 |
+
def __init__(
|
562 |
+
self,
|
563 |
+
tokenizer=None
|
564 |
+
):
|
565 |
+
parse_tasks = []
|
566 |
+
parse_task_configs = {}
|
567 |
+
config = self._create_default_config()
|
568 |
+
for task in config['PARSE_TASKS']:
|
569 |
+
parse_tasks.append(task['TASK_NAME'])
|
570 |
+
parse_task_configs[task['TASK_NAME']] = task
|
571 |
+
|
572 |
+
self.config = config
|
573 |
+
self.parse_tasks = parse_tasks
|
574 |
+
self.parse_tasks_configs = parse_task_configs
|
575 |
+
|
576 |
+
self.tokenizer = tokenizer
|
577 |
+
if self.tokenizer is not None:
|
578 |
+
self.all_special_tokens = set(self.tokenizer.all_special_tokens)
|
579 |
+
|
580 |
+
self.init_quantizers()
|
581 |
+
self.black_list_of_phrase_grounding = self._create_black_list_of_phrase_grounding()
|
582 |
+
|
583 |
+
def _create_black_list_of_phrase_grounding(self):
|
584 |
+
black_list = {}
|
585 |
+
|
586 |
+
if 'phrase_grounding' in self.parse_tasks and self.parse_tasks_configs['phrase_grounding']['FILTER_BY_BLACK_LIST']:
|
587 |
+
black_list = set(
|
588 |
+
['it', 'I', 'me', 'mine',
|
589 |
+
'you', 'your', 'yours',
|
590 |
+
'he', 'him', 'his',
|
591 |
+
'she', 'her', 'hers',
|
592 |
+
'they', 'them', 'their', 'theirs',
|
593 |
+
'one', 'oneself',
|
594 |
+
'we', 'us', 'our', 'ours',
|
595 |
+
'you', 'your', 'yours',
|
596 |
+
'they', 'them', 'their', 'theirs',
|
597 |
+
'mine', 'yours', 'his', 'hers', 'its',
|
598 |
+
'ours', 'yours', 'theirs',
|
599 |
+
'myself', 'yourself', 'himself', 'herself', 'itself',
|
600 |
+
'ourselves', 'yourselves', 'themselves',
|
601 |
+
'this', 'that',
|
602 |
+
'these', 'those',
|
603 |
+
'who', 'whom', 'whose', 'which', 'what',
|
604 |
+
'who', 'whom', 'whose', 'which', 'that',
|
605 |
+
'all', 'another', 'any', 'anybody', 'anyone', 'anything',
|
606 |
+
'each', 'everybody', 'everyone', 'everything',
|
607 |
+
'few', 'many', 'nobody', 'none', 'one', 'several',
|
608 |
+
'some', 'somebody', 'someone', 'something',
|
609 |
+
'each other', 'one another',
|
610 |
+
'myself', 'yourself', 'himself', 'herself', 'itself',
|
611 |
+
'ourselves', 'yourselves', 'themselves',
|
612 |
+
'the image', 'image', 'images', 'the', 'a', 'an', 'a group',
|
613 |
+
'other objects', 'lots', 'a set',
|
614 |
+
]
|
615 |
+
)
|
616 |
+
|
617 |
+
return black_list
|
618 |
+
|
619 |
+
def _create_default_config(self):
|
620 |
+
config = {
|
621 |
+
'NUM_BBOX_HEIGHT_BINS': 1000,
|
622 |
+
'NUM_BBOX_WIDTH_BINS': 1000,
|
623 |
+
'BOX_QUANTIZATION_MODE': 'floor',
|
624 |
+
'COORDINATES_HEIGHT_BINS': 1000,
|
625 |
+
'COORDINATES_WIDTH_BINS': 1000,
|
626 |
+
'COORDINATES_QUANTIZATION_MODE': 'floor',
|
627 |
+
'PARSE_TASKS': [
|
628 |
+
{
|
629 |
+
'TASK_NAME': 'od',
|
630 |
+
'PATTERN': r'([a-zA-Z0-9 ]+)<loc_(\\d+)><loc_(\\d+)><loc_(\\d+)><loc_(\\d+)>'
|
631 |
+
},
|
632 |
+
{
|
633 |
+
'TASK_NAME': 'ocr',
|
634 |
+
'PATTERN': r'(.+?)<loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)>',
|
635 |
+
'AREA_THRESHOLD': 0.01
|
636 |
+
},
|
637 |
+
{
|
638 |
+
'TASK_NAME': 'phrase_grounding',
|
639 |
+
'FILTER_BY_BLACK_LIST': True
|
640 |
+
},
|
641 |
+
{
|
642 |
+
'TASK_NAME': 'pure_text',
|
643 |
+
},
|
644 |
+
{
|
645 |
+
'TASK_NAME': 'description_with_bboxes',
|
646 |
+
},
|
647 |
+
{
|
648 |
+
'TASK_NAME': 'description_with_polygons',
|
649 |
+
},
|
650 |
+
{
|
651 |
+
'TASK_NAME': 'polygons',
|
652 |
+
},
|
653 |
+
{
|
654 |
+
'TASK_NAME': 'bboxes',
|
655 |
+
},
|
656 |
+
{
|
657 |
+
'TASK_NAME': 'description_with_bboxes_or_polygons',
|
658 |
+
}
|
659 |
+
]
|
660 |
+
}
|
661 |
+
|
662 |
+
return config
|
663 |
+
|
664 |
+
def init_quantizers(self):
|
665 |
+
# we have box_quantizer (od, grounding) and coordinates_quantizer (ocr, referring_segmentation)
|
666 |
+
num_bbox_height_bins = self.config.get('NUM_BBOX_HEIGHT_BINS', 1000)
|
667 |
+
num_bbox_width_bins = self.config.get('NUM_BBOX_WIDTH_BINS', 1000)
|
668 |
+
box_quantization_mode = self.config.get('BOX_QUANTIZATION_MODE', 'floor')
|
669 |
+
self.box_quantizer = BoxQuantizer(
|
670 |
+
box_quantization_mode,
|
671 |
+
(num_bbox_width_bins, num_bbox_height_bins),
|
672 |
+
)
|
673 |
+
|
674 |
+
num_bbox_height_bins = self.config['COORDINATES_HEIGHT_BINS'] if 'COORDINATES_HEIGHT_BINS' in self.config else self.config.get('NUM_BBOX_HEIGHT_BINS', 1000)
|
675 |
+
num_bbox_width_bins = self.config['COORDINATES_WIDTH_BINS'] if 'COORDINATES_WIDTH_BINS' in self.config else self.config.get('NUM_BBOX_WIDTH_BINS', 1000)
|
676 |
+
box_quantization_mode = self.config.get('COORDINATES_QUANTIZATION_MODE') if 'COORDINATES_QUANTIZATION_MODE' in self.config else self.config.get('BOX_QUANTIZATION_MODE', 'floor')
|
677 |
+
self.coordinates_quantizer = CoordinatesQuantizer(
|
678 |
+
box_quantization_mode,
|
679 |
+
(num_bbox_width_bins, num_bbox_height_bins),
|
680 |
+
)
|
681 |
+
|
682 |
+
def decode_with_spans(self, tokenizer, token_ids):
|
683 |
+
filtered_tokens = tokenizer.convert_ids_to_tokens(
|
684 |
+
token_ids, skip_special_tokens=False)
|
685 |
+
assert len(filtered_tokens) == len(token_ids)
|
686 |
+
|
687 |
+
# To avoid mixing byte-level and unicode for byte-level BPT
|
688 |
+
# we need to build string separately for added tokens and byte-level tokens
|
689 |
+
# cf. https://github.com/huggingface/transformers/issues/1133
|
690 |
+
sub_texts = []
|
691 |
+
for token in filtered_tokens:
|
692 |
+
if token in self.all_special_tokens:
|
693 |
+
sub_texts.append(token)
|
694 |
+
else:
|
695 |
+
if isinstance(tokenizer, (BartTokenizer, BartTokenizerFast)):
|
696 |
+
sub_text = tokenizer.convert_tokens_to_string([token])
|
697 |
+
elif isinstance(tokenizer, (T5Tokenizer, T5TokenizerFast)):
|
698 |
+
# Ref: https://github.com/google/sentencepiece#whitespace-is-treated-as-a-basic-symbol
|
699 |
+
# Note: Do not strip sub_text as it may have functional whitespace
|
700 |
+
sub_text = token.replace('▁', ' ')
|
701 |
+
else:
|
702 |
+
raise ValueError(f'type {type(tokenizer)} not supported')
|
703 |
+
sub_texts.append(sub_text)
|
704 |
+
|
705 |
+
text = ''
|
706 |
+
spans = []
|
707 |
+
for sub_text in sub_texts:
|
708 |
+
span = (len(text), len(text) + len(sub_text)) # [start index, end index).
|
709 |
+
text += sub_text
|
710 |
+
spans.append(span)
|
711 |
+
|
712 |
+
# Text format:
|
713 |
+
# 1. T5Tokenizer/T5TokenizerFast:
|
714 |
+
# "<loc_1><loc_2><loc_3><loc_4> transplanting dog<loc_1><loc_2><loc_3><loc_4> cat</s>"
|
715 |
+
# Equivalent to t5_tokenizer.decode(input_ids, skip_special_tokens=False, clean_up_tokenization_spaces=False, spaces_between_special_tokens=False)
|
716 |
+
# 2. BartTokenizer (need to double check):
|
717 |
+
# "<s><loc_1><loc_2><loc_3><loc_4>transplanting dog<loc_1><loc_2><loc_3><loc_4>cat</s>"
|
718 |
+
# Equivalent to bart_tokenizer.decode(input_ids, skip_special_tokens=False, clean_up_tokenization_spaces=False, spaces_between_special_tokens=False)
|
719 |
+
return text, spans
|
720 |
+
|
721 |
+
def parse_od_from_text_and_spans(
|
722 |
+
self,
|
723 |
+
text,
|
724 |
+
pattern,
|
725 |
+
image_size,
|
726 |
+
phrase_centric=False
|
727 |
+
):
|
728 |
+
parsed = list(re.finditer(pattern, text))
|
729 |
+
|
730 |
+
instances = []
|
731 |
+
for i in range(len(parsed)):
|
732 |
+
# Prepare instance.
|
733 |
+
instance = {}
|
734 |
+
|
735 |
+
if phrase_centric:
|
736 |
+
bbox_bins = [int(parsed[i].group(j)) for j in range(2, 6)]
|
737 |
+
else:
|
738 |
+
bbox_bins = [int(parsed[i].group(j)) for j in range(1, 5)]
|
739 |
+
instance['bbox'] = self.box_quantizer.dequantize(
|
740 |
+
boxes=torch.tensor(bbox_bins),
|
741 |
+
size=image_size
|
742 |
+
).tolist()
|
743 |
+
|
744 |
+
if phrase_centric:
|
745 |
+
instance['cat_name'] = parsed[i].group(1).lower().strip()
|
746 |
+
else:
|
747 |
+
instance['cat_name'] = parsed[i].group(5).lower().strip()
|
748 |
+
instances.append(instance)
|
749 |
+
|
750 |
+
return instances
|
751 |
+
|
752 |
+
def parse_ocr_from_text_and_spans(self,
|
753 |
+
text,
|
754 |
+
pattern,
|
755 |
+
image_size,
|
756 |
+
area_threshold=-1.0,
|
757 |
+
):
|
758 |
+
bboxes = []
|
759 |
+
labels = []
|
760 |
+
text = text.replace('<s>', '')
|
761 |
+
# ocr with regions
|
762 |
+
parsed = re.findall(pattern, text)
|
763 |
+
instances = []
|
764 |
+
image_width, image_height = image_size
|
765 |
+
|
766 |
+
for ocr_line in parsed:
|
767 |
+
ocr_content = ocr_line[0]
|
768 |
+
quad_box = ocr_line[1:]
|
769 |
+
quad_box = [int(i) for i in quad_box]
|
770 |
+
quad_box = self.coordinates_quantizer.dequantize(
|
771 |
+
torch.tensor(np.array(quad_box).reshape(-1, 2)),
|
772 |
+
size=image_size
|
773 |
+
).reshape(-1).tolist()
|
774 |
+
|
775 |
+
if area_threshold > 0:
|
776 |
+
x_coords = [i for i in quad_box[0::2]]
|
777 |
+
y_coords = [i for i in quad_box[1::2]]
|
778 |
+
|
779 |
+
# apply the Shoelace formula
|
780 |
+
area = 0.5 * abs(sum(x_coords[i] * y_coords[i + 1] - x_coords[i + 1] * y_coords[i] for i in range(4 - 1)))
|
781 |
+
|
782 |
+
if area < (image_width * image_height) * area_threshold:
|
783 |
+
continue
|
784 |
+
|
785 |
+
bboxes.append(quad_box)
|
786 |
+
labels.append(ocr_content)
|
787 |
+
instances.append({
|
788 |
+
'quad_box': quad_box,
|
789 |
+
'text': ocr_content,
|
790 |
+
})
|
791 |
+
return instances
|
792 |
+
|
793 |
+
def parse_phrase_grounding_from_text_and_spans(self, text, pattern, image_size):
|
794 |
+
# ignore <s> </s> and <pad>
|
795 |
+
cur_span = 0
|
796 |
+
if text.startswith('<s>'):
|
797 |
+
cur_span += 3
|
798 |
+
|
799 |
+
text = text.replace('<s>', '')
|
800 |
+
text = text.replace('</s>', '')
|
801 |
+
text = text.replace('<pad>', '')
|
802 |
+
|
803 |
+
pattern = r"([^<]+(?:<loc_\d+>){4,})"
|
804 |
+
phrases = re.findall(pattern, text)
|
805 |
+
|
806 |
+
# pattern should be text pattern and od pattern
|
807 |
+
pattern = r'^\s*(.*?)(?=<od>|</od>|<box>|</box>|<bbox>|</bbox>|<loc_)'
|
808 |
+
box_pattern = r'<loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)>'
|
809 |
+
|
810 |
+
instances = []
|
811 |
+
for pharse_text in phrases:
|
812 |
+
phrase_text_strip = pharse_text.replace('<ground>', '', 1)
|
813 |
+
phrase_text_strip = pharse_text.replace('<obj>', '', 1)
|
814 |
+
|
815 |
+
if phrase_text_strip == '':
|
816 |
+
cur_span += len(pharse_text)
|
817 |
+
continue
|
818 |
+
|
819 |
+
# Prepare instance.
|
820 |
+
instance = {}
|
821 |
+
|
822 |
+
# parse phrase, get string
|
823 |
+
phrase = re.search(pattern, phrase_text_strip)
|
824 |
+
if phrase is None:
|
825 |
+
cur_span += len(pharse_text)
|
826 |
+
continue
|
827 |
+
|
828 |
+
# parse bboxes by box_pattern
|
829 |
+
bboxes_parsed = list(re.finditer(box_pattern, pharse_text))
|
830 |
+
if len(bboxes_parsed) == 0:
|
831 |
+
cur_span += len(pharse_text)
|
832 |
+
continue
|
833 |
+
|
834 |
+
phrase = phrase.group()
|
835 |
+
# remove leading and trailing spaces
|
836 |
+
phrase = phrase.strip()
|
837 |
+
|
838 |
+
if phrase in self.black_list_of_phrase_grounding:
|
839 |
+
cur_span += len(pharse_text)
|
840 |
+
continue
|
841 |
+
|
842 |
+
# a list of list
|
843 |
+
bbox_bins = [[int(_bboxes_parsed.group(j)) for j in range(1, 5)] for _bboxes_parsed in bboxes_parsed]
|
844 |
+
instance['bbox'] = self.box_quantizer.dequantize(
|
845 |
+
boxes=torch.tensor(bbox_bins),
|
846 |
+
size=image_size
|
847 |
+
).tolist()
|
848 |
+
|
849 |
+
# exclude non-ascii characters
|
850 |
+
phrase = phrase.encode('ascii',errors='ignore').decode('ascii')
|
851 |
+
instance['cat_name'] = phrase
|
852 |
+
|
853 |
+
instances.append(instance)
|
854 |
+
|
855 |
+
return instances
|
856 |
+
|
857 |
+
def parse_description_with_bboxes_from_text_and_spans(self, text, pattern, image_size, allow_empty_phrase=False):
|
858 |
+
# temporary parse solution, split by '.'
|
859 |
+
# ignore <s> </s> and <pad>
|
860 |
+
|
861 |
+
text = text.replace('<s>', '')
|
862 |
+
text = text.replace('</s>', '')
|
863 |
+
text = text.replace('<pad>', '')
|
864 |
+
|
865 |
+
if allow_empty_phrase:
|
866 |
+
pattern = rf"(?:(?:<loc_\d+>){{4,}})"
|
867 |
+
else:
|
868 |
+
pattern = r"([^<]+(?:<loc_\d+>){4,})"
|
869 |
+
phrases = re.findall(pattern, text)
|
870 |
+
|
871 |
+
# pattern should be text pattern and od pattern
|
872 |
+
pattern = r'^\s*(.*?)(?=<od>|</od>|<box>|</box>|<bbox>|</bbox>|<loc_)'
|
873 |
+
box_pattern = r'<loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)>'
|
874 |
+
|
875 |
+
instances = []
|
876 |
+
for pharse_text in phrases:
|
877 |
+
phrase_text_strip = pharse_text.replace('<ground>', '', 1)
|
878 |
+
phrase_text_strip = pharse_text.replace('<obj>', '', 1)
|
879 |
+
|
880 |
+
if phrase_text_strip == '' and not allow_empty_phrase:
|
881 |
+
continue
|
882 |
+
|
883 |
+
# parse phrase, get string
|
884 |
+
phrase = re.search(pattern, phrase_text_strip)
|
885 |
+
if phrase is None:
|
886 |
+
continue
|
887 |
+
|
888 |
+
phrase = phrase.group()
|
889 |
+
# remove leading and trailing spaces
|
890 |
+
phrase = phrase.strip()
|
891 |
+
|
892 |
+
# parse bboxes by box_pattern
|
893 |
+
bboxes_parsed = list(re.finditer(box_pattern, pharse_text))
|
894 |
+
if len(bboxes_parsed) == 0:
|
895 |
+
continue
|
896 |
+
|
897 |
+
# a list of list
|
898 |
+
bbox_bins = [[int(_bboxes_parsed.group(j)) for j in range(1, 5)] for _bboxes_parsed in bboxes_parsed]
|
899 |
+
|
900 |
+
bboxes = self.box_quantizer.dequantize(
|
901 |
+
boxes=torch.tensor(bbox_bins),
|
902 |
+
size=image_size
|
903 |
+
).tolist()
|
904 |
+
|
905 |
+
phrase = phrase.encode('ascii',errors='ignore').decode('ascii')
|
906 |
+
for _bboxes in bboxes:
|
907 |
+
# Prepare instance.
|
908 |
+
instance = {}
|
909 |
+
instance['bbox'] = _bboxes
|
910 |
+
# exclude non-ascii characters
|
911 |
+
instance['cat_name'] = phrase
|
912 |
+
instances.append(instance)
|
913 |
+
|
914 |
+
return instances
|
915 |
+
|
916 |
+
def parse_description_with_polygons_from_text_and_spans(self, text, pattern, image_size,
|
917 |
+
allow_empty_phrase=False,
|
918 |
+
polygon_sep_token='<sep>',
|
919 |
+
polygon_start_token='<poly>',
|
920 |
+
polygon_end_token='</poly>',
|
921 |
+
with_box_at_start=False,
|
922 |
+
):
|
923 |
+
|
924 |
+
# ref_seg format: '<expression><x1><y1><x2><y2><><><sep><><><><>'
|
925 |
+
# ignore <s> </s> and <pad>
|
926 |
+
|
927 |
+
text = text.replace('<s>', '')
|
928 |
+
text = text.replace('</s>', '')
|
929 |
+
text = text.replace('<pad>', '')
|
930 |
+
|
931 |
+
if allow_empty_phrase:
|
932 |
+
pattern = rf"(?:(?:<loc_\d+>|{re.escape(polygon_sep_token)}|{re.escape(polygon_start_token)}|{re.escape(polygon_end_token)}){{4,}})"
|
933 |
+
else:
|
934 |
+
# [^<]+: This part matches one or more characters that are not the < symbol.
|
935 |
+
# The ^ inside the square brackets [] is a negation, meaning it matches anything except <.
|
936 |
+
#
|
937 |
+
pattern = rf"([^<]+(?:<loc_\d+>|{re.escape(polygon_sep_token)}|{re.escape(polygon_start_token)}|{re.escape(polygon_end_token)}){{4,}})"
|
938 |
+
phrases = re.findall(pattern, text)
|
939 |
+
|
940 |
+
phrase_string_pattern = r'^\s*(.*?)(?=<od>|</od>|<box>|</box>|<bbox>|</bbox>|<loc_|<poly>)'
|
941 |
+
box_pattern = rf'((?:<loc_\d+>)+)(?:{re.escape(polygon_sep_token)}|$)'
|
942 |
+
|
943 |
+
# one polygons instance is separated by polygon_start_token and polygon_end_token
|
944 |
+
polygons_instance_pattern = rf'{re.escape(polygon_start_token)}(.*?){re.escape(polygon_end_token)}'
|
945 |
+
|
946 |
+
instances = []
|
947 |
+
for phrase_text in phrases:
|
948 |
+
|
949 |
+
# exclude loc_\d+>
|
950 |
+
# need to get span if want to include category score
|
951 |
+
phrase_text_strip = re.sub(r'^loc_\d+>', '', phrase_text, count=1)
|
952 |
+
|
953 |
+
# phrase = phrase.replace('<poly>', '')
|
954 |
+
# phrase = phrase.replace('poly>', '')
|
955 |
+
|
956 |
+
if phrase_text_strip == '' and not allow_empty_phrase:
|
957 |
+
continue
|
958 |
+
|
959 |
+
|
960 |
+
# parse phrase, get string
|
961 |
+
phrase = re.search(phrase_string_pattern, phrase_text_strip)
|
962 |
+
if phrase is None:
|
963 |
+
continue
|
964 |
+
phrase = phrase.group()
|
965 |
+
# remove leading and trailing spaces
|
966 |
+
phrase = phrase.strip()
|
967 |
+
|
968 |
+
# parse bboxes by box_pattern
|
969 |
+
|
970 |
+
# split by polygon_start_token and polygon_end_token first using polygons_instance_pattern
|
971 |
+
if polygon_start_token in phrase_text and polygon_end_token in phrase_text:
|
972 |
+
polygons_instances_parsed = list(re.finditer(polygons_instance_pattern, phrase_text))
|
973 |
+
else:
|
974 |
+
polygons_instances_parsed = [phrase_text]
|
975 |
+
|
976 |
+
for _polygons_instances_parsed in polygons_instances_parsed:
|
977 |
+
# Prepare instance.
|
978 |
+
instance = {}
|
979 |
+
|
980 |
+
# polygons_parsed= list(re.finditer(box_pattern, phrase_text))
|
981 |
+
if isinstance(_polygons_instances_parsed, str):
|
982 |
+
polygons_parsed= list(re.finditer(box_pattern, _polygons_instances_parsed))
|
983 |
+
else:
|
984 |
+
polygons_parsed= list(re.finditer(box_pattern, _polygons_instances_parsed.group(1)))
|
985 |
+
if len(polygons_parsed) == 0:
|
986 |
+
continue
|
987 |
+
|
988 |
+
# a list of list (polygon)
|
989 |
+
bbox = []
|
990 |
+
polygons = []
|
991 |
+
for _polygon_parsed in polygons_parsed:
|
992 |
+
# group 1: whole <loc_\d+>...</loc_\d+>
|
993 |
+
_polygon = _polygon_parsed.group(1)
|
994 |
+
# parse into list of int
|
995 |
+
_polygon = [int(_loc_parsed.group(1)) for _loc_parsed in re.finditer(r'<loc_(\d+)>', _polygon)]
|
996 |
+
if with_box_at_start and len(bbox) == 0:
|
997 |
+
if len(_polygon) > 4:
|
998 |
+
# no valid bbox prediction
|
999 |
+
bbox = _polygon[:4]
|
1000 |
+
_polygon = _polygon[4:]
|
1001 |
+
else:
|
1002 |
+
bbox = [0, 0, 0, 0]
|
1003 |
+
# abandon last element if is not paired
|
1004 |
+
if len(_polygon) % 2 == 1:
|
1005 |
+
_polygon = _polygon[:-1]
|
1006 |
+
|
1007 |
+
# reshape into (n, 2)
|
1008 |
+
_polygon = self.coordinates_quantizer.dequantize(
|
1009 |
+
torch.tensor(np.array(_polygon).reshape(-1, 2)),
|
1010 |
+
size=image_size
|
1011 |
+
).reshape(-1).tolist()
|
1012 |
+
# reshape back
|
1013 |
+
polygons.append(_polygon)
|
1014 |
+
|
1015 |
+
instance['cat_name'] = phrase
|
1016 |
+
instance['polygons'] = polygons
|
1017 |
+
if len(bbox) != 0:
|
1018 |
+
instance['bbox'] = self.box_quantizer.dequantize(
|
1019 |
+
boxes=torch.tensor([bbox]),
|
1020 |
+
size=image_size
|
1021 |
+
).tolist()[0]
|
1022 |
+
|
1023 |
+
instances.append(instance)
|
1024 |
+
|
1025 |
+
return instances
|
1026 |
+
|
1027 |
+
def __call__(
|
1028 |
+
self,
|
1029 |
+
text=None,
|
1030 |
+
image_size=None,
|
1031 |
+
parse_tasks=None,
|
1032 |
+
):
|
1033 |
+
"""
|
1034 |
+
Args:
|
1035 |
+
text: model outputs
|
1036 |
+
image_size: (width, height)
|
1037 |
+
parse_tasks: a list of tasks to parse, if None, parse all tasks.
|
1038 |
+
|
1039 |
+
"""
|
1040 |
+
if parse_tasks is not None:
|
1041 |
+
if isinstance(parse_tasks, str):
|
1042 |
+
parse_tasks = [parse_tasks]
|
1043 |
+
for _parse_task in parse_tasks:
|
1044 |
+
assert _parse_task in self.parse_tasks, f'parse task {_parse_task} not supported'
|
1045 |
+
|
1046 |
+
# sequence or text should be provided
|
1047 |
+
assert text is not None, 'text should be provided'
|
1048 |
+
|
1049 |
+
parsed_dict = {
|
1050 |
+
'text': text
|
1051 |
+
}
|
1052 |
+
|
1053 |
+
for task in self.parse_tasks:
|
1054 |
+
if parse_tasks is not None and task not in parse_tasks:
|
1055 |
+
continue
|
1056 |
+
|
1057 |
+
pattern = self.parse_tasks_configs[task].get('PATTERN', None)
|
1058 |
+
|
1059 |
+
if task == 'ocr':
|
1060 |
+
instances = self.parse_ocr_from_text_and_spans(
|
1061 |
+
text,
|
1062 |
+
pattern=pattern,
|
1063 |
+
image_size=image_size,
|
1064 |
+
area_threshold=self.parse_tasks_configs[task].get('AREA_THRESHOLD', 0.01),
|
1065 |
+
)
|
1066 |
+
parsed_dict['ocr'] = instances
|
1067 |
+
elif task == 'phrase_grounding':
|
1068 |
+
instances = self.parse_phrase_grounding_from_text_and_spans(
|
1069 |
+
text,
|
1070 |
+
pattern=pattern,
|
1071 |
+
image_size=image_size,
|
1072 |
+
)
|
1073 |
+
parsed_dict['phrase_grounding'] = instances
|
1074 |
+
elif task == 'pure_text':
|
1075 |
+
parsed_dict['pure_text'] = text
|
1076 |
+
elif task == 'description_with_bboxes':
|
1077 |
+
instances = self.parse_description_with_bboxes_from_text_and_spans(
|
1078 |
+
text,
|
1079 |
+
pattern=pattern,
|
1080 |
+
image_size=image_size,
|
1081 |
+
)
|
1082 |
+
parsed_dict['description_with_bboxes'] = instances
|
1083 |
+
elif task == 'description_with_polygons':
|
1084 |
+
instances = self.parse_description_with_polygons_from_text_and_spans(
|
1085 |
+
text,
|
1086 |
+
pattern=pattern,
|
1087 |
+
image_size=image_size,
|
1088 |
+
)
|
1089 |
+
parsed_dict['description_with_polygons'] = instances
|
1090 |
+
elif task == 'polygons':
|
1091 |
+
instances = self.parse_description_with_polygons_from_text_and_spans(
|
1092 |
+
text,
|
1093 |
+
pattern=pattern,
|
1094 |
+
image_size=image_size,
|
1095 |
+
allow_empty_phrase=True,
|
1096 |
+
)
|
1097 |
+
parsed_dict['polygons'] = instances
|
1098 |
+
elif task == 'bboxes':
|
1099 |
+
instances = self.parse_description_with_bboxes_from_text_and_spans(
|
1100 |
+
text,
|
1101 |
+
pattern=pattern,
|
1102 |
+
image_size=image_size,
|
1103 |
+
allow_empty_phrase=True,
|
1104 |
+
)
|
1105 |
+
parsed_dict['bboxes'] = instances
|
1106 |
+
elif task == 'description_with_bboxes_or_polygons':
|
1107 |
+
if '<poly>' in text:
|
1108 |
+
# only support either polygons or bboxes, not both at the same time
|
1109 |
+
instances = self.parse_description_with_polygons_from_text_and_spans(
|
1110 |
+
text,
|
1111 |
+
pattern=pattern,
|
1112 |
+
image_size=image_size,
|
1113 |
+
)
|
1114 |
+
else:
|
1115 |
+
instances = self.parse_description_with_bboxes_from_text_and_spans(
|
1116 |
+
text,
|
1117 |
+
pattern=pattern,
|
1118 |
+
image_size=image_size,
|
1119 |
+
)
|
1120 |
+
parsed_dict['description_with_bboxes_or_polygons'] = instances
|
1121 |
+
else:
|
1122 |
+
raise ValueError("task {} is not supported".format(task))
|
1123 |
+
|
1124 |
+
return parsed_dict
|
vision_tower/processor_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoProcessor": "processing_florence2.Florence2Processor"
|
4 |
+
},
|
5 |
+
"processor_class": "Florence2Processor"
|
6 |
+
}
|
vision_tower/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d63827e77ae378597498dc090baf676bc39771b4ca28a8804c312452cb3f146
|
3 |
+
size 1645700830
|
vision_tower/special_tokens_map.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vision_tower/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vision_tower/tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
vision_tower/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|