Hugging Face's logo

onnx-community
/
paligemma2-3b-pt-896

Image-Text-to-Text
Transformers.js
ONNX
paligemma
Model card Files Community
Xenova HF staff commited on
Commit
8a33316
•
1 Parent(s): 19b4b50

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-896",
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": 4096,
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": 896,
46
+ "intermediate_size": 4304,
47
+ "model_type": "siglip_vision_model",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 27,
50
+ "num_image_tokens": 4096,
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": 4096
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:dcc8c6384325e19da6881af28cec8060cff9b5c590bbff87c55e0ea75ad7017d
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 sha256:25aefc2f93f54a121cd837d036093dc88979d7402f40ea3be6dc37de7a7c2290
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 sha256:4f4b899da11ed68b3f3042e1c2875ac3c48b685b7e19a84999d2c26c0cf1d825
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 sha256:485b9121dee539d8eefd410146234c66b354d249c3de51bca3be09f18d584f16
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:f2979f30bfc039cb93f95f4a3d99d2d28c7cbd49d9f082919d0f7cf3a1c4dbe3
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 sha256:5141fd9fd65271cf2dd90e84125b9d9856a260b879c36b711551f2da8ee35fd5
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 sha256:3fcce2518bc0ab3740608102d3c315b9159c9d2b61d2fd647559c0872b715f0e
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 sha256:468f191e29132f28d3e83ab72c3e618d1d8f8d3b01a371f88ea6083cef9247ca
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:f2979f30bfc039cb93f95f4a3d99d2d28c7cbd49d9f082919d0f7cf3a1c4dbe3
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 sha256:17d912a7ac0ec6f6c7ffd018e0f4b643b0b33d4be07743de8ada37654fbefc8e
3
+ size 1113126
onnx/decoder_model_merged_uint8.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854ea329bb765a8f87cd8d81a7dcd77cb1f03f55248b6e69776bd0d9e3b89b1c
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:f21cb408273c150939c4819b6f7b5acfd9da82e97dd4b246841e21f9d0afabb3
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:f21cb408273c150939c4819b6f7b5acfd9da82e97dd4b246841e21f9d0afabb3
3
+ size 2370502656
onnx/embed_tokens_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698b67df152e2e76fefc5afc541932a55504c70156f78aa8f2732c2eca98adaa
3
+ size 1185251719
onnx/embed_tokens_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5d5881d5cc3e646c9385ef31610b77b487797085c2e0698eb966ecac3c6d5b
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:f21cb408273c150939c4819b6f7b5acfd9da82e97dd4b246841e21f9d0afabb3
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:b420f83d17150456ba3fb4ad5065b6d0497d0dff0873e8f16e59a6ae3ca9ff55
3
+ size 1185251738
onnx/embed_tokens_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5d5881d5cc3e646c9385ef31610b77b487797085c2e0698eb966ecac3c6d5b
3
+ size 592626210
onnx/embed_tokens_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5d5881d5cc3e646c9385ef31610b77b487797085c2e0698eb966ecac3c6d5b
3
+ size 592626210
onnx/vision_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6e6ee3c998bc595ffe07dcde300eade0705162e30da181533e35613de36acc
3
+ size 1678681814
onnx/vision_encoder_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623b05f121b686f9dea16d1661be2de4d93ab788899abba7d458d088d0efe155
3
+ size 256528862
onnx/vision_encoder_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821d6c268497b0f14f86fa0761a4562e393fd98346e137dbdb02a174151d641f
3
+ size 839636876
onnx/vision_encoder_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0331df26fb32ea2b94dc5c3499e613ba51ed728ee01987e6283a4056ed4f1583
3
+ size 435723060
onnx/vision_encoder_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10838f2be5a00cabc7d3404e48f5b16e510220e7ef0b09e93fb4e22e23f90a77
3
+ size 282696364
onnx/vision_encoder_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6fa0eab073c8a9d5b27303aba09bd1937de990878bc6c7bacd54d4276038a7
3
+ size 245211873
onnx/vision_encoder_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53b618b2f8da499e196139e9732700e5de8ebae6364f3877a89be47e989b3a7
3
+ size 435723145
onnx/vision_encoder_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53b618b2f8da499e196139e9732700e5de8ebae6364f3877a89be47e989b3a7
3
+ size 435723145
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": 4096,
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": 896,
23
+ "width": 896
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