Upload folder using huggingface_hub
Browse files- config.json +20 -8
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -19,16 +19,27 @@
|
|
19 |
"conv_dim_out": 1024,
|
20 |
"conv_use_xavier_init": true,
|
21 |
"eos_token_id": 7,
|
22 |
-
"full_attn_idxs": [
|
23 |
-
2,
|
24 |
-
5,
|
25 |
-
8,
|
26 |
-
10,
|
27 |
-
12,
|
28 |
-
14
|
29 |
-
],
|
30 |
"hidden_size": 1024,
|
31 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"max_position_embeddings": 128000,
|
33 |
"model_type": "lfm2",
|
34 |
"norm_eps": 1e-05,
|
@@ -40,6 +51,7 @@
|
|
40 |
"rope_theta": 1000000.0,
|
41 |
"torch_dtype": "bfloat16",
|
42 |
"transformers_version": "4.54.0.dev0",
|
|
|
43 |
"use_cache": true,
|
44 |
"use_pos_enc": true,
|
45 |
"vocab_size": 65536
|
|
|
19 |
"conv_dim_out": 1024,
|
20 |
"conv_use_xavier_init": true,
|
21 |
"eos_token_id": 7,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"hidden_size": 1024,
|
23 |
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 6656,
|
25 |
+
"layer_types": [
|
26 |
+
"conv",
|
27 |
+
"conv",
|
28 |
+
"full_attention",
|
29 |
+
"conv",
|
30 |
+
"conv",
|
31 |
+
"full_attention",
|
32 |
+
"conv",
|
33 |
+
"conv",
|
34 |
+
"full_attention",
|
35 |
+
"conv",
|
36 |
+
"full_attention",
|
37 |
+
"conv",
|
38 |
+
"full_attention",
|
39 |
+
"conv",
|
40 |
+
"full_attention",
|
41 |
+
"conv"
|
42 |
+
],
|
43 |
"max_position_embeddings": 128000,
|
44 |
"model_type": "lfm2",
|
45 |
"norm_eps": 1e-05,
|
|
|
51 |
"rope_theta": 1000000.0,
|
52 |
"torch_dtype": "bfloat16",
|
53 |
"transformers_version": "4.54.0.dev0",
|
54 |
+
"unsloth_fixed": true,
|
55 |
"use_cache": true,
|
56 |
"use_pos_enc": true,
|
57 |
"vocab_size": 65536
|
tokenizer_config.json
CHANGED
@@ -4064,7 +4064,7 @@
|
|
4064 |
"eos_token": "<|im_end|>",
|
4065 |
"extra_special_tokens": {},
|
4066 |
"legacy": false,
|
4067 |
-
"model_max_length":
|
4068 |
"pad_token": "<|pad|>",
|
4069 |
"padding_side": "left",
|
4070 |
"sp_model_kwargs": {},
|
|
|
4064 |
"eos_token": "<|im_end|>",
|
4065 |
"extra_special_tokens": {},
|
4066 |
"legacy": false,
|
4067 |
+
"model_max_length": 128000,
|
4068 |
"pad_token": "<|pad|>",
|
4069 |
"padding_side": "left",
|
4070 |
"sp_model_kwargs": {},
|