google/paligemma2-3b-pt-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-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 |
+
"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 sha256:08133e5dce273309b7730f22c6532d8f0aeafcc6aa104cb444dc87f417660a0d
|
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 sha256:87bbd5d438d98955460bae6b84aa65d8279a1f9e71f2d968db26b4b89525ae8e
|
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 sha256:606649da5fe87df072653321405462fa5cf005f6413ef6703168c99ff1e73aff
|
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 sha256:0f44596c007d29f355dd1939dd73dce53d28b34c462bc7805b733dbf5ecccab3
|
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:f05130b5aedae8c0c2fc038d279bd4455a953eba6b372e02d4d89322a6ea2783
|
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:f8706ffe1d3781b4a8b2a59aae7d4c748f2cfeb18bc957fd9022687cdc7e5b60
|
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:cea95d61dbb4a32744e4cca3b91f7a313efa815f139848a81164ae6ac34e41cb
|
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 sha256:142e11d1b16124f7d933003ddcdd597df0c5c268d5fccdc316506f787e7d2077
|
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 sha256:798b1de0c2bcf6a91276ce005514579060ffd716e7ce07cf7eb10f0f722e2fc7
|
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: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 sha256:9811c483a8116a90b6c4f57478b0ad35ad1929f4364dbb2b93fdadc9d8f81059
|
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: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 sha256:30c861251a489c4fa6abdb24d956de091b39ad9e6fe086a98df5a8fb1d9c4661
|
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: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_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30c861251a489c4fa6abdb24d956de091b39ad9e6fe086a98df5a8fb1d9c4661
|
3 |
+
size 592626147
|
onnx/vision_encoder.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3e77cb8065747f8eea23a9653260e56edcf0802c13e7acf50bc8dc4d2cb4f2f
|
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:cd8ee9a15a3441bf85906937f374a33ab706a8b1c0040f5263e62626a982d2c7
|
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:eceba8119b8898242d72493c0c89a3798805ca0e6cd5f004cb22822cead305b4
|
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:be5a5491157da8c745fa046e123be332b3b88b1ebdb0f4601668ff6b820348ae
|
3 |
+
size 418936865
|
onnx/vision_encoder_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d89d42ffa4cd1b13647aab301ecc045c57c7f20f8c201f291b0ef2c618afeee
|
3 |
+
size 240097695
|
onnx/vision_encoder_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0760c9ab9ad55c69ab8475a83803ba0e7624f21607f90a5821e28e864fbe12ed
|
3 |
+
size 224375011
|
onnx/vision_encoder_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09815edecbff06fdca35fe4fedd43dd309ca6c1244b1a278c27b661d40a6f81a
|
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
|
|