Hugging Face's logo

Qiorios
/
seed0_sample5000_bmlama_google-gemma-3-12b-pt_en-el_1.0-1.0_1.0

Safetensors
gemma3
Model card Files
xet
Community
Qiorios commited on
Commit
68878a5
·
verified ·
1 Parent(s): 2a0124a

End of training

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. config.json +107 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00005.safetensors +3 -0
  6. model-00002-of-00005.safetensors +3 -0
  7. model-00003-of-00005.safetensors +3 -0
  8. model-00004-of-00005.safetensors +3 -0
  9. model-00005-of-00005.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
  11. special_tokens_map.json +33 -0
  12. tokenizer.json +3 -0
  13. tokenizer.model +3 -0
  14. tokenizer_config.json +0 -0
  15. training_args.bin +3 -0
.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 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "_sliding_window_pattern": 6,
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_logit_softcapping": null,
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
+ "layer_types": [
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "full_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention"
71
+ ],
72
+ "max_position_embeddings": 131072,
73
+ "model_type": "gemma3_text",
74
+ "num_attention_heads": 16,
75
+ "num_hidden_layers": 48,
76
+ "num_key_value_heads": 8,
77
+ "query_pre_attn_scalar": 256,
78
+ "rms_norm_eps": 1e-06,
79
+ "rope_local_base_freq": 10000.0,
80
+ "rope_scaling": {
81
+ "factor": 8.0,
82
+ "rope_type": "linear"
83
+ },
84
+ "rope_theta": 1000000.0,
85
+ "sliding_window": 1024,
86
+ "torch_dtype": "bfloat16",
87
+ "use_cache": true,
88
+ "vocab_size": 262208
89
+ },
90
+ "torch_dtype": "bfloat16",
91
+ "transformers_version": "4.55.0",
92
+ "vision_config": {
93
+ "attention_dropout": 0.0,
94
+ "hidden_act": "gelu_pytorch_tanh",
95
+ "hidden_size": 1152,
96
+ "image_size": 896,
97
+ "intermediate_size": 4304,
98
+ "layer_norm_eps": 1e-06,
99
+ "model_type": "siglip_vision_model",
100
+ "num_attention_heads": 16,
101
+ "num_channels": 3,
102
+ "num_hidden_layers": 27,
103
+ "patch_size": 14,
104
+ "torch_dtype": "bfloat16",
105
+ "vision_use_head": false
106
+ }
107
+ }
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": "4.55.0"
13
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809bd10b2fbb55af9fd0414535f7f1aa4934cc0cbbdc30075af9dd91dc9fd1d9
3
+ size 4979902192
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7fa7224b7d2db9dbfe9f5e872dc39fa72f5b3a2c145c54ebf2ccba7f0e47dcf
3
+ size 4931296592
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b9e1705f795606e0557439d1cc93271f89dfa7a7baac2113fb128f5885945d
3
+ size 4931296656
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7633e936e92f0de3439115db64fd8ab6c18ba5318fd3566a2703a3be067c60e9
3
+ size 4931296656
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5977b346d2a2571851602706c21324a4a165b89678552e95df3b0cd569e69c3f
3
+ size 4601000928
model.safetensors.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.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
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
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f10327d87b75bfb4e1aa1271ed1c5afed137456835893cf140b7b7930624159
3
+ size 6929