Pclanglais commited on
Commit
ceda062
·
verified ·
1 Parent(s): d78cac7

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4782cd56c1d8cdcc9ed434be613d0290d775d2b6ce5a91e3b398489ea3c27b2
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 sha256:6c03385432e9770fb336dde44ffde0d3fe65f0877775ff681ff8bc4e89c83a38
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:ac69d0434fc1d328339d998485fe66a4d3eb31e5dd824b7c3e72a96c9c5cd7fa
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:ac44b2e646c837e9b0e0a423e019ab2ed9778c516817139731b4ef7455788a49
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 sha256:4908c92ee165a253b7cf4bbd911984545dd73832028dcb1902b964e3dc9f3788
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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6852f8d561078cc0cebe70ca03c5bfdd0d60a45f9d2e0e1e4cc05b68e9ec329e
3
+ size 33385008
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