Hugging Face's logo

onnx-community
/
paligemma2-3b-pt-224

Image-Text-to-Text
Transformers.js
ONNX
paligemma
Model card Files Community
1
Xenova HF staff commited on
Commit
8e75c2d
·
verified ·
1 Parent(s): c454762

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. .gitattributes +9 -0
  2. config.json +56 -0
  3. generation_config.json +8 -0
  4. onnx/decoder_model_merged.onnx +3 -0
  5. onnx/decoder_model_merged.onnx_data +3 -0
  6. onnx/decoder_model_merged_bnb4.onnx +3 -0
  7. onnx/decoder_model_merged_fp16.onnx +3 -0
  8. onnx/decoder_model_merged_fp16.onnx_data +3 -0
  9. onnx/decoder_model_merged_int8.onnx +3 -0
  10. onnx/decoder_model_merged_int8.onnx_data +3 -0
  11. onnx/decoder_model_merged_q4.onnx +3 -0
  12. onnx/decoder_model_merged_q4f16.onnx +3 -0
  13. onnx/decoder_model_merged_quantized.onnx +3 -0
  14. onnx/decoder_model_merged_quantized.onnx_data +3 -0
  15. onnx/decoder_model_merged_uint8.onnx +3 -0
  16. onnx/decoder_model_merged_uint8.onnx_data +3 -0
  17. onnx/embed_tokens.onnx +3 -0
  18. onnx/embed_tokens.onnx_data +3 -0
  19. onnx/embed_tokens_bnb4.onnx +3 -0
  20. onnx/embed_tokens_bnb4.onnx_data +3 -0
  21. onnx/embed_tokens_fp16.onnx +3 -0
  22. onnx/embed_tokens_int8.onnx +3 -0
  23. onnx/embed_tokens_q4.onnx +3 -0
  24. onnx/embed_tokens_q4.onnx_data +3 -0
  25. onnx/embed_tokens_q4f16.onnx +3 -0
  26. onnx/embed_tokens_quantized.onnx +3 -0
  27. onnx/embed_tokens_uint8.onnx +3 -0
  28. onnx/vision_encoder.onnx +3 -0
  29. onnx/vision_encoder_bnb4.onnx +3 -0
  30. onnx/vision_encoder_fp16.onnx +3 -0
  31. onnx/vision_encoder_int8.onnx +3 -0
  32. onnx/vision_encoder_q4.onnx +3 -0
  33. onnx/vision_encoder_q4f16.onnx +3 -0
  34. onnx/vision_encoder_quantized.onnx +3 -0
  35. onnx/vision_encoder_uint8.onnx +3 -0
  36. preprocessor_config.json +25 -0
  37. special_tokens_map.json +39 -0
  38. tokenizer.json +3 -0
  39. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,12 @@ 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_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/decoder_model_merged_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text
41
+ onnx/embed_tokens.onnx_data filter=lfs diff=lfs merge=lfs -text
42
+ onnx/embed_tokens_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
43
+ onnx/embed_tokens_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
44
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "google/paligemma2-3b-pt-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
+ "num_image_tokens": 256,
15
+ "pad_token_id": 0,
16
+ "projection_dim": 2304,
17
+ "text_config": {
18
+ "architectures": [
19
+ "Gemma2ForCausalLM"
20
+ ],
21
+ "attn_logit_softcapping": 50.0,
22
+ "cache_implementation": "hybrid",
23
+ "eos_token_id": [
24
+ 1,
25
+ 107
26
+ ],
27
+ "final_logit_softcapping": 30.0,
28
+ "hidden_act": "gelu_pytorch_tanh",
29
+ "hidden_activation": "gelu_pytorch_tanh",
30
+ "hidden_size": 2304,
31
+ "intermediate_size": 9216,
32
+ "model_type": "gemma2",
33
+ "num_hidden_layers": 26,
34
+ "num_image_tokens": 256,
35
+ "num_key_value_heads": 4,
36
+ "query_pre_attn_scalar": 256,
37
+ "sliding_window": 4096,
38
+ "torch_dtype": "bfloat16",
39
+ "vocab_size": 257216
40
+ },
41
+ "torch_dtype": "bfloat16",
42
+ "transformers_version": "4.48.0.dev0",
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
+ }
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": "4.48.0.dev0"
8
+ }
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ee4b02af21e4b89218d0101866193223e40e5f079d6a3d053e31a05305b3ed
3
+ size 911907
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08133e5dce273309b7730f22c6532d8f0aeafcc6aa104cb444dc87f417660a0d
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 sha256:8c963778257cb06aa979e7c321f49168dc1bd8ed1fd4277c56b932133db2597f
3
+ size 1473893028
onnx/decoder_model_merged_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12dcfe9f371d437bc7c8611aaef1076d4ae549133c8902d7dceedbb98d3bd813
3
+ size 926613
onnx/decoder_model_merged_fp16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606649da5fe87df072653321405462fa5cf005f6413ef6703168c99ff1e73aff
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 sha256:4c564f9aca693bd6b9409d2c0319dde0a25cf41d8702a3f4788ec17fc81e2d5e
3
+ size 1112739
onnx/decoder_model_merged_int8.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b219d6bc508c1c51be2a92c53af112db37a9f6b0faa22e5a26b872d6e56302cd
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:a9bf358108f7274a8782b44beb85a5bf5dfed96fe0ab5516fef827067f14c388
3
+ size 1637447967
onnx/decoder_model_merged_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623c00e5d69dc386ce58b4da4fa99753a1cacf4201d894ac8eed063b7bcb33ef
3
+ size 1473420972
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ef7f641f430ea012309bba53af5476e75ba8db0f30aadf4618660adb43b567d
3
+ size 1114187
onnx/decoder_model_merged_quantized.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b219d6bc508c1c51be2a92c53af112db37a9f6b0faa22e5a26b872d6e56302cd
3
+ size 2617869312
onnx/decoder_model_merged_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ce33b2ef0b473ed43780ccec6320e3b373529c86507a7cf557624c9d883ce4
3
+ size 1113124
onnx/decoder_model_merged_uint8.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6eb4dbf383b873105b331c91549f3cff3e0c6333cc81c5ee0bc24fef45d4f3a
3
+ size 2617869312
onnx/embed_tokens.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec4d04aa26664472e46a8b42ab7f202880650cdc8e6009bad63779a1550ce2f
3
+ size 362
onnx/embed_tokens.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9169a3d7a6b3137a2742a5a2f2c12c631003135129aeff732710fc36ba14bcc
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:af38d768206cdcad29ebfb2401ee215233892f5f31236637001f093281783ce5
3
+ size 386
onnx/embed_tokens_bnb4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9169a3d7a6b3137a2742a5a2f2c12c631003135129aeff732710fc36ba14bcc
3
+ size 2370502656
onnx/embed_tokens_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e432b03a69fc60447652ae1cc75b5fac24f3c2a6d379943d99fd15509e5e643
3
+ size 1185251719
onnx/embed_tokens_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3855caef3bc17c938fc3317592985783170341a6251ac48b52cb5855c94052f8
3
+ size 592626210
onnx/embed_tokens_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d3f2894bddbf8cc11162ad77d93462941ccd690738ba9ccfeff2995c18db4a
3
+ size 384
onnx/embed_tokens_q4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9169a3d7a6b3137a2742a5a2f2c12c631003135129aeff732710fc36ba14bcc
3
+ size 2370502656
onnx/embed_tokens_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27399d801a9b7baa090b33b87c5b6cb19c2018769e6f38d24ad3e9e75dbeb96f
3
+ size 1185251738
onnx/embed_tokens_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3855caef3bc17c938fc3317592985783170341a6251ac48b52cb5855c94052f8
3
+ size 592626210
onnx/embed_tokens_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3855caef3bc17c938fc3317592985783170341a6251ac48b52cb5855c94052f8
3
+ size 592626210
onnx/vision_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96795aff8535661040d4e20946ccec8c2dae9d07b7b9e9eb6c96d692539a283d
3
+ size 1660987092
onnx/vision_encoder_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d2a923df3f2caaa35d52186ee8c5555a127411eba8f62afc6cdb89247ca5be9
3
+ size 238834140
onnx/vision_encoder_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fe85b351ccf7b244610f8273f2525ed89ddc870df68f6c79ebeb66af588625
3
+ size 830789514
onnx/vision_encoder_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0903100de9446b9479be43c6701cd501b4df82a13280b13b99b4ee5d0dd6e1
3
+ size 418028338
onnx/vision_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbaf9aad93f378c26b7e1c751f3aecf665d72ec85cff774bcc0351f86c14a0f
3
+ size 265001641
onnx/vision_encoder_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d698406a1da8137474b688c30117a0d1f288cf4b8b950881cde2f6ee4c58367
3
+ size 236364511
onnx/vision_encoder_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcdc097a9cff7329632ac2468511c898739881113f52e7ae5a9cf7db9c42835
3
+ size 418028421
onnx/vision_encoder_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcdc097a9cff7329632ac2468511c898739881113f52e7ae5a9cf7db9c42835
3
+ size 418028421
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 sha256:172fab587d68c56b63eb3620057c62dfd15e503079ff7fce584692e3fd5bf4da
3
+ size 34600820
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff