google/paligemma2-3b-mix-224 ONNX
Browse files- .gitattributes +8 -0
- config.json +57 -0
- generation_config.json +8 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged.onnx_data +3 -0
- onnx/decoder_model_merged_bnb4.onnx +3 -0
- onnx/decoder_model_merged_fp16.onnx +3 -0
- onnx/decoder_model_merged_fp16.onnx_data +3 -0
- onnx/decoder_model_merged_int8.onnx +3 -0
- onnx/decoder_model_merged_int8.onnx_data +3 -0
- onnx/decoder_model_merged_q4.onnx +3 -0
- onnx/decoder_model_merged_q4f16.onnx +3 -0
- onnx/decoder_model_merged_uint8.onnx +3 -0
- onnx/decoder_model_merged_uint8.onnx_data +3 -0
- onnx/embed_tokens.onnx +3 -0
- onnx/embed_tokens.onnx_data +3 -0
- onnx/embed_tokens_bnb4.onnx +3 -0
- onnx/embed_tokens_bnb4.onnx_data +3 -0
- onnx/embed_tokens_fp16.onnx +3 -0
- onnx/embed_tokens_int8.onnx +3 -0
- onnx/embed_tokens_q4.onnx +3 -0
- onnx/embed_tokens_q4.onnx_data +3 -0
- onnx/embed_tokens_q4f16.onnx +3 -0
- onnx/embed_tokens_uint8.onnx +3 -0
- onnx/vision_encoder.onnx +3 -0
- onnx/vision_encoder_bnb4.onnx +3 -0
- onnx/vision_encoder_fp16.onnx +3 -0
- onnx/vision_encoder_int8.onnx +3 -0
- onnx/vision_encoder_q4.onnx +3 -0
- onnx/vision_encoder_q4f16.onnx +3 -0
- onnx/vision_encoder_uint8.onnx +3 -0
- preprocessor_config.json +25 -0
- special_tokens_map.json +39 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
|
37 |
+
onnx/decoder_model_merged_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
|
38 |
+
onnx/decoder_model_merged_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
|
39 |
+
onnx/decoder_model_merged_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text
|
40 |
+
onnx/embed_tokens.onnx_data filter=lfs diff=lfs merge=lfs -text
|
41 |
+
onnx/embed_tokens_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
|
42 |
+
onnx/embed_tokens_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
|
43 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "google/paligemma2-3b-mix-224",
|
4 |
+
"_vocab_size": 257152,
|
5 |
+
"architectures": [
|
6 |
+
"PaliGemmaForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"image_token_index": 257152,
|
12 |
+
"model_type": "paligemma",
|
13 |
+
"num_hidden_layers": 26,
|
14 |
+
"pad_token_id": 0,
|
15 |
+
"projection_dim": 2304,
|
16 |
+
"text_config": {
|
17 |
+
"architectures": [
|
18 |
+
"Gemma2ForCausalLM"
|
19 |
+
],
|
20 |
+
"attn_logit_softcapping": 50.0,
|
21 |
+
"cache_implementation": "hybrid",
|
22 |
+
"eos_token_id": [
|
23 |
+
1,
|
24 |
+
107
|
25 |
+
],
|
26 |
+
"final_logit_softcapping": 30.0,
|
27 |
+
"hidden_act": "gelu_pytorch_tanh",
|
28 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
29 |
+
"hidden_size": 2304,
|
30 |
+
"intermediate_size": 9216,
|
31 |
+
"model_type": "gemma2",
|
32 |
+
"num_hidden_layers": 26,
|
33 |
+
"num_image_tokens": 256,
|
34 |
+
"num_key_value_heads": 4,
|
35 |
+
"query_pre_attn_scalar": 256,
|
36 |
+
"sliding_window": 4096,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"vocab_size": 257216,
|
39 |
+
"head_dim": 256
|
40 |
+
},
|
41 |
+
"torch_dtype": "bfloat16",
|
42 |
+
"transformers_version": "4.48.3",
|
43 |
+
"vision_config": {
|
44 |
+
"hidden_size": 1152,
|
45 |
+
"intermediate_size": 4304,
|
46 |
+
"model_type": "siglip_vision_model",
|
47 |
+
"num_attention_heads": 16,
|
48 |
+
"num_hidden_layers": 27,
|
49 |
+
"num_image_tokens": 256,
|
50 |
+
"num_positions": 256,
|
51 |
+
"patch_size": 14,
|
52 |
+
"projection_dim": 2304,
|
53 |
+
"torch_dtype": "bfloat16",
|
54 |
+
"vision_use_head": false
|
55 |
+
},
|
56 |
+
"num_image_tokens": 256
|
57 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"cache_implementation": "hybrid",
|
5 |
+
"eos_token_id": 1,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.48.3"
|
8 |
+
}
|
onnx/decoder_model_merged.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5dabb55bd2405a486f77fbab4a973e6abc9f97d812b6240bc43dc7fd0400ad4
|
3 |
+
size 1810134
|
onnx/decoder_model_merged.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cff92f6e1448623116c69d3a4cc268ed7bce93a121f453bb692bb06e400f416b
|
3 |
+
size 10468574208
|
onnx/decoder_model_merged_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bdf87562ae8d6ffaa9a0a87d29ba9a5ca8931f252183f140233feea91036f3e
|
3 |
+
size 1474791267
|
onnx/decoder_model_merged_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8715fb1fa1ce74093671a15577919a1f78960610e6416c78f1ec15fc4f36246
|
3 |
+
size 1828660
|
onnx/decoder_model_merged_fp16.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb4f43f7eccdb3bfc7d1886cda46750a04bc73f1ba94a3e8b77cece95d54a4dc
|
3 |
+
size 5234287104
|
onnx/decoder_model_merged_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db80441c9e1de27e48518d0f5b16d2e16ec6e88b58f19097f8f7016d545ef489
|
3 |
+
size 6825776
|
onnx/decoder_model_merged_int8.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94e2fd9244f02b24a6985ff1f57ed14d4d10ffe1df80a941bcf47baad224e245
|
3 |
+
size 2617869312
|
onnx/decoder_model_merged_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c47e90837c5600f5a2a4f3a62fc55546a581def00f65ce72f1122983ca215444
|
3 |
+
size 1474793907
|
onnx/decoder_model_merged_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22939d4c1f95ec606074accfa4b1f32c8aa5b6aca324ca7bcf99c39e275ca382
|
3 |
+
size 1392549064
|
onnx/decoder_model_merged_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18073058a264801d9c73d877cb5fbc9b1ed44676daae230e3d52a867d13bbe6f
|
3 |
+
size 6826069
|
onnx/decoder_model_merged_uint8.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dbabf1a997ab22dc7b3242684596d67cb57c491d4be4a2b6cc5997925e8a2ac
|
3 |
+
size 2617869312
|
onnx/embed_tokens.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:214da7721dea427f645e465446f175bcf055f6c4a99208fad598f8d4c46491ad
|
3 |
+
size 299
|
onnx/embed_tokens.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd25834b7bcbbc6570ea5c710f1fbed20000bf7f4abe027f51e3b25f8805478
|
3 |
+
size 2370502656
|
onnx/embed_tokens_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9811c483a8116a90b6c4f57478b0ad35ad1929f4364dbb2b93fdadc9d8f81059
|
3 |
+
size 323
|
onnx/embed_tokens_bnb4.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd25834b7bcbbc6570ea5c710f1fbed20000bf7f4abe027f51e3b25f8805478
|
3 |
+
size 2370502656
|
onnx/embed_tokens_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89e320b6c8902a8d58c0f447b25fc0431f95e39af9007af1f5225cba114c3d69
|
3 |
+
size 1185251719
|
onnx/embed_tokens_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c325127f7d62ae1fa47153b82546a486d692169ae5ce7ddb96c1d556acc70798
|
3 |
+
size 592626147
|
onnx/embed_tokens_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4386b62c9808310612e2d06ad4d5f8401980b15c30dcbb403cc85107f77cbbb
|
3 |
+
size 321
|
onnx/embed_tokens_q4.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bd25834b7bcbbc6570ea5c710f1fbed20000bf7f4abe027f51e3b25f8805478
|
3 |
+
size 2370502656
|
onnx/embed_tokens_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18b32d5c51b8a23e44bc75af79c69edfa4f53b2f19f129cb1b8eea5e002cee70
|
3 |
+
size 1185251738
|
onnx/embed_tokens_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c325127f7d62ae1fa47153b82546a486d692169ae5ce7ddb96c1d556acc70798
|
3 |
+
size 592626147
|
onnx/vision_encoder.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e24164eca54f2c6bc76c3668faa4329071e1a45291b861b4a366d157efdbf49
|
3 |
+
size 1661408448
|
onnx/vision_encoder_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd006226ba96ad33d2de2d994d11bf34d7571701954086791d1ea415183d358c
|
3 |
+
size 239255496
|
onnx/vision_encoder_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1a16a03973202d4a4e023a99d247af349c33918017d94e0957075346336313c
|
3 |
+
size 831211972
|
onnx/vision_encoder_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f7c817394a63a13f51b513fbaee4cd1d080bcf5ce3f46476d5589f2f03eb549
|
3 |
+
size 418936865
|
onnx/vision_encoder_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ab20eb56db08cb131d411cfc832d2a06600c539b3e0c1fc4b57d351b080cf6c
|
3 |
+
size 240097695
|
onnx/vision_encoder_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b49fd6f3acda113fb94743bfb678c1a06a6f363066df675ee873189f8c714d35
|
3 |
+
size 224375011
|
onnx/vision_encoder_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d23039a41d03da9edb4f65cac12377ca602cb680f2404555a7a01114b68dc6c
|
3 |
+
size 418936865
|
preprocessor_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_processor_type": "SiglipImageProcessor",
|
12 |
+
"image_seq_length": 256,
|
13 |
+
"image_std": [
|
14 |
+
0.5,
|
15 |
+
0.5,
|
16 |
+
0.5
|
17 |
+
],
|
18 |
+
"processor_class": "PaliGemmaProcessor",
|
19 |
+
"resample": 3,
|
20 |
+
"rescale_factor": 0.00392156862745098,
|
21 |
+
"size": {
|
22 |
+
"height": 224,
|
23 |
+
"width": 224
|
24 |
+
}
|
25 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<image>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
],
|
11 |
+
"bos_token": {
|
12 |
+
"content": "<bos>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"eos_token": {
|
19 |
+
"content": "<eos>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"pad_token": {
|
26 |
+
"content": "<pad>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"unk_token": {
|
33 |
+
"content": "<unk>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
}
|
39 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3c3a19458f6053993ad11f9cf1ff4590fa1649cd3d04344233385c08c2cbb8
|
3 |
+
size 18650602
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|