Hugging Face's logo

onnx-community
/
paligemma2-3b-ft-docci-448

Image-Text-to-Text
Transformers.js
ONNX
paligemma
Model card Files Community
Xenova HF staff commited on
Commit
4b4e4dd
·
verified ·
1 Parent(s): 2eb93c3

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. .gitattributes +9 -0
  2. config.json +58 -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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "google/paligemma2-3b-ft-docci-448",
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": 1024,
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": "4.48.0.dev0",
43
+ "vision_config": {
44
+ "hidden_size": 1152,
45
+ "image_size": 448,
46
+ "intermediate_size": 4304,
47
+ "model_type": "siglip_vision_model",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 27,
50
+ "num_image_tokens": 1024,
51
+ "num_positions": 256,
52
+ "patch_size": 14,
53
+ "projection_dim": 2304,
54
+ "torch_dtype": "bfloat16",
55
+ "vision_use_head": false
56
+ },
57
+ "num_image_tokens": 1024
58
+ }
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:c96d4f2342e5e8ac981d8a09830c5770590c39e4f58f2a5c7b0d7d2fb4abda79
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 sha256:2abb6e863e491db9f536c2014301863afdd4982ab71a79a3b86774b90952c79a
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:c07146972b53ea93343e523ff3ca81de3e7ceff5c647a41d7c936b0f2486976f
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:e5c9a0031c6056fcf4ae58a7dc073b4cbae5d7e3dad6df1fd1effff08534515d
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 sha256:9974ce5dbc88eacd451e7eff4f995d0decd9036d59f5cef3b50be2792cbb02a1
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:bb4c7bd66514603d6d25653d8fbfa0dd9e5c677ebc92bce6d416492667552870
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:bf9147b4c828a1885a6f0cfa37f94b3ac5fe232d1c6d5d09a17ca16e042e553f
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:fbf7bf0daf1a23c09c85564a84db04ad729c475cf12fddbccd3a6167c53464c3
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 sha256:9974ce5dbc88eacd451e7eff4f995d0decd9036d59f5cef3b50be2792cbb02a1
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 sha256:034e488102675275c9cd4aed244a8d3e840d84fcf7574bb61aeff487d2f923e8
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 sha256:4e7d8107cfbafa55ac79e1839a0665d178aed4abbd1e7920594ad1141beeeba8
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:e8d9e3284e62c57dc30619de19b951b8facabf25ef6efed208d9062a81e7f87f
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:e8d9e3284e62c57dc30619de19b951b8facabf25ef6efed208d9062a81e7f87f
3
+ size 2370502656
onnx/embed_tokens_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999452247dffe86fbde2cd14a1addf39120f18ff71d1a64243e1bc563f79c50b
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:ee0098e63ef11fa6fa1bc6c6c760894668e8bbb7781f5aee458b2e04b2f0a8e5
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:e8d9e3284e62c57dc30619de19b951b8facabf25ef6efed208d9062a81e7f87f
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:f2eae6051de4040d1f7a728977d5a086835199fb0c943aa3347885566ffe5e91
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:ee0098e63ef11fa6fa1bc6c6c760894668e8bbb7781f5aee458b2e04b2f0a8e5
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:ee0098e63ef11fa6fa1bc6c6c760894668e8bbb7781f5aee458b2e04b2f0a8e5
3
+ size 592626210
onnx/vision_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668a2b37bed80950506e89cbf6d7595f2da30f0d89eebcfdf116899cfc137a35
3
+ size 1664526038
onnx/vision_encoder_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9e5500c147602ad3d6071d7305afcd302e0d855327dbe93ff27126cce86e7d
3
+ size 242373086
onnx/vision_encoder_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be4bb84d91742e08588f072be2d547e141948c07bfd2058b7ac45b0c5aa5bad4
3
+ size 832558988
onnx/vision_encoder_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91f29ad98dff9f7e32c8dc8fb8b3e971ba0adbc5c13032ad422ed99384568e3
3
+ size 421567284
onnx/vision_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb72b3025003d7fe3a5c2ea697f82bcbbe4d022a32d2ed3ec11e2f1930a896f
3
+ size 268540588
onnx/vision_encoder_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3859e4499ef8621f87ead8fc0fe178c19a3cc40e49f58b29a14f1027dc41725f
3
+ size 238133985
onnx/vision_encoder_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077449a96c00667846494bcc79812e3a9abe29d2a787af8eacab3ccbe51a4ccd
3
+ size 421567369
onnx/vision_encoder_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077449a96c00667846494bcc79812e3a9abe29d2a787af8eacab3ccbe51a4ccd
3
+ size 421567369
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": 1024,
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": 448,
23
+ "width": 448
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