Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +58 -0
- generation_config.json +13 -0
- preprocessor_config.json +29 -0
- processor_config.json +4 -0
- pytorch_model-00001-of-00005.bin +3 -0
- pytorch_model-00002-of-00005.bin +3 -0
- pytorch_model-00003-of-00005.bin +3 -0
- pytorch_model-00004-of-00005.bin +3 -0
- pytorch_model-00005-of-00005.bin +3 -0
- pytorch_model.bin.index.json +0 -0
- special_tokens_map.json +33 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"eoi_token_index": 256000,
|
| 7 |
+
"image_token_index": 262144,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"mm_tokens_per_image": 256,
|
| 10 |
+
"model_type": "gemma3",
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_logit_softcapping": null,
|
| 15 |
+
"cache_implementation": "hybrid",
|
| 16 |
+
"final_logit_softcapping": null,
|
| 17 |
+
"head_dim": 256,
|
| 18 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 19 |
+
"hidden_size": 3840,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 15360,
|
| 22 |
+
"max_position_embeddings": 131072,
|
| 23 |
+
"model_type": "gemma3_text",
|
| 24 |
+
"num_attention_heads": 16,
|
| 25 |
+
"num_hidden_layers": 48,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"query_pre_attn_scalar": 256,
|
| 28 |
+
"rms_norm_eps": 1e-06,
|
| 29 |
+
"rope_local_base_freq": 10000.0,
|
| 30 |
+
"rope_scaling": {
|
| 31 |
+
"factor": 8.0,
|
| 32 |
+
"rope_type": "linear"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 1000000.0,
|
| 35 |
+
"sliding_window": 1024,
|
| 36 |
+
"sliding_window_pattern": 6,
|
| 37 |
+
"torch_dtype": "bfloat16",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 262208
|
| 40 |
+
},
|
| 41 |
+
"torch_dtype": "bfloat16",
|
| 42 |
+
"transformers_version": "4.52.4",
|
| 43 |
+
"vision_config": {
|
| 44 |
+
"attention_dropout": 0.0,
|
| 45 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 46 |
+
"hidden_size": 1152,
|
| 47 |
+
"image_size": 896,
|
| 48 |
+
"intermediate_size": 4304,
|
| 49 |
+
"layer_norm_eps": 1e-06,
|
| 50 |
+
"model_type": "siglip_vision_model",
|
| 51 |
+
"num_attention_heads": 16,
|
| 52 |
+
"num_channels": 3,
|
| 53 |
+
"num_hidden_layers": 27,
|
| 54 |
+
"patch_size": 14,
|
| 55 |
+
"torch_dtype": "bfloat16",
|
| 56 |
+
"vision_use_head": false
|
| 57 |
+
}
|
| 58 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "hybrid",
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
1,
|
| 7 |
+
106
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"top_k": 64,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.52.4"
|
| 13 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
pytorch_model-00001-of-00005.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dd077ccf06fe3012e9cbe06253f1559b41ffd5ed3d5866bd604d24c71e3a343
|
| 3 |
+
size 4980020746
|
pytorch_model-00002-of-00005.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f644e4fe9e970ddc301ff123bf094d1b358dea6d27de717bd519c5008c06279e
|
| 3 |
+
size 4931330903
|
pytorch_model-00003-of-00005.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c2dabe43b093ff52db69a3c7c0e92fe7a0005386e9a7271215832ae0eb2a9d2
|
| 3 |
+
size 4931330967
|
pytorch_model-00004-of-00005.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff23f5b5ec9741d0303c334bc64cc048ca6027569f8839e3df0b473c9a2c0734
|
| 3 |
+
size 4931330967
|
pytorch_model-00005-of-00005.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aeb78454f16cc1d781cf00458ed0b9453681ad34a940504e448188bbe394329
|
| 3 |
+
size 4601033386
|
pytorch_model.bin.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|