Hugging Face's logo

onnx-community
/
paligemma2-3b-pt-448

Image-to-Text
Transformers.js
ONNX
paligemma
Model card Files
xet
Community
Xenova HF Staff commited on
Commit
6b0bcf2
·
verified ·
1 Parent(s): def3d0c

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-pt-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:be381081ecc4d5498c07e1f86d0c0dfa2182ee559ed6ca60284913d192bead8b
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:e1ef817b344624b52e3e13c56830816459be0e740e80e295ef647a7c4d7a9c83
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:c520d335085179fb55fb942535d03b928688537a9170a7cc699fe29b5acaeb5a
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 sha256:6447733f145f8edcfbe94dca9536a397332792520fa52f99af4b976e86ad907b
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 sha256:80135d594c6d09b9f4183024882e0ccaba4387d40cf26de2b82a633430b3d300
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 sha256:4b35df4b7fe8553c7b5267edf07f9408b37cfb3e73b1ecf1201c72d1f1a985f0
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 sha256:4e7543440e5b3a3b4a60cedeeaa67c225a50e74b57d1821b00f0b9d888537773
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 sha256:5b7776fc350f60e2bd3b5c48c77e01986c2d1576e393c78f9e49f76d0f4749d0
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 sha256:80135d594c6d09b9f4183024882e0ccaba4387d40cf26de2b82a633430b3d300
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:a498fb899e42ff928028d6c132399f51d78ada6ed5bfd62f7053cb737db3472c
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:a33e4e45e7d1dfd93eb63aca70924db75bce3da46a76d2a5663f2751a941e18c
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 sha256:3034918dec3b27db9c537eed09e6fc29e70150efed0c791b37886be22740c5b1
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 sha256:3034918dec3b27db9c537eed09e6fc29e70150efed0c791b37886be22740c5b1
3
+ size 2370502656
onnx/embed_tokens_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da4a7313619c3ed2070011a84bdc6aa3df2e02e26f0a77a24232c322dfffe11
3
+ size 1185251719
onnx/embed_tokens_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd8e095d8fe8323c47337f8d5f3ed9fc789ae6f84e5b5005151805ef577b1d1
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 sha256:3034918dec3b27db9c537eed09e6fc29e70150efed0c791b37886be22740c5b1
3
+ size 2370502656
onnx/embed_tokens_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e959cc5671b6511c0668bf85414bdcbea1007105ffe467d3a9139d48e544f53
3
+ size 1185251738
onnx/embed_tokens_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd8e095d8fe8323c47337f8d5f3ed9fc789ae6f84e5b5005151805ef577b1d1
3
+ size 592626210
onnx/embed_tokens_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd8e095d8fe8323c47337f8d5f3ed9fc789ae6f84e5b5005151805ef577b1d1
3
+ size 592626210
onnx/vision_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae56db4c27998b99bc258588242292efbfea29111b8c29aa69d3f3be67b1f02
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:dc1965939c2cecf36fc28a32d37fc7f0863a1b504b0c24e71f609c45b4b7e496
3
+ size 242373086
onnx/vision_encoder_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef868196f32ab9a887924e68182cc5fcf008f99df7debc9fcce138123415cd2
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:fc0bfb73d6305d6e2249ad275a10d36255c60a66251b604693a515d82724016c
3
+ size 421567284
onnx/vision_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edf46b2b7f6e849fb043bcb0b163f71d01f36517ba8e9bc04b05b4a9c75216b
3
+ size 268540588
onnx/vision_encoder_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8235135ab0a302935348b5c20eff858270a9b00591c7b50f3666fa17bd3d8042
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:de0520188d0e91224720c0bfebe7a1237e3e909ad3778a100e986bb1328183a0
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:de0520188d0e91224720c0bfebe7a1237e3e909ad3778a100e986bb1328183a0
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