Hugging Face's logo

egemensert
/
inek-99qpt-gemma-3-12b-it

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
gemma3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files Metrics Community
egemensert commited on
Commit
1d7b5d3
·
verified ·
1 Parent(s): c5c589f

Upload Gemma3ForConditionalGeneration

Browse files
Files changed (15) hide show
  1. config.json +62 -0
  2. generation_config.json +13 -0
  3. model-00001-of-00012.safetensors +3 -0
  4. model-00002-of-00012.safetensors +3 -0
  5. model-00003-of-00012.safetensors +3 -0
  6. model-00004-of-00012.safetensors +3 -0
  7. model-00005-of-00012.safetensors +3 -0
  8. model-00006-of-00012.safetensors +3 -0
  9. model-00007-of-00012.safetensors +3 -0
  10. model-00008-of-00012.safetensors +3 -0
  11. model-00009-of-00012.safetensors +3 -0
  12. model-00010-of-00012.safetensors +3 -0
  13. model-00011-of-00012.safetensors +3 -0
  14. model-00012-of-00012.safetensors +3 -0
  15. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "text_config": {
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "attn_logit_softcapping": null,
19
+ "cache_implementation": "hybrid",
20
+ "final_logit_softcapping": null,
21
+ "head_dim": 256,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 3840,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 15360,
26
+ "max_position_embeddings": 131072,
27
+ "model_type": "gemma3_text",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 48,
30
+ "num_key_value_heads": 8,
31
+ "query_pre_attn_scalar": 256,
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_local_base_freq": 10000.0,
34
+ "rope_scaling": {
35
+ "factor": 8.0,
36
+ "rope_type": "linear"
37
+ },
38
+ "rope_theta": 1000000.0,
39
+ "sliding_window": 1024,
40
+ "sliding_window_pattern": 6,
41
+ "torch_dtype": "float32",
42
+ "use_cache": true,
43
+ "vocab_size": 262208
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.50.0",
47
+ "vision_config": {
48
+ "attention_dropout": 0.0,
49
+ "hidden_act": "gelu_pytorch_tanh",
50
+ "hidden_size": 1152,
51
+ "image_size": 896,
52
+ "intermediate_size": 4304,
53
+ "layer_norm_eps": 1e-06,
54
+ "model_type": "siglip_vision_model",
55
+ "num_attention_heads": 16,
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 27,
58
+ "patch_size": 14,
59
+ "torch_dtype": "float32",
60
+ "vision_use_head": false
61
+ }
62
+ }
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": "4.50.0"
13
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84ee8a00c054bac06f29e8c287c2de2698258d89e53175d8f172bc62f0620c0
3
+ size 1685223128
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e82ee3069f9d984a48b97f9bd848afe7d48f2cf6c245014f0b33237f3993c727
3
+ size 4987027384
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cca68afa210f2547f6e4bfc5e9afc2e6e35ba15eb1932553e52e72f88349a56
3
+ size 4844749824
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eceebc1fb277a7d7ad6bae423a72f657ca21d1c1bf51235284c2b894364f3ee3
3
+ size 4954909736
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fba42de0eafaec141d7bb54bf5c51bb1157721f4a7c3edbe6872289626ab2e9
3
+ size 4907664584
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459e5e175bdf4d02895e61c29d1c2524378006c212f1a6c04742d0ba2ce78524
3
+ size 4954909792
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84184ee3aebd5d3ee12415e511776e0174e714f45c166a646fb90d62de78e058
3
+ size 4907664584
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee960716dc5d0d6cd533fd4b173b72dd9f68c70ee643ce92392432603912c02
3
+ size 4954909792
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12401262c5eda13372e96ddc45f68c8c8c32df97dd3fb0882b6418b2ff61c589
3
+ size 4907664584
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6fa076c01dc5594bb8073a910fef8d613cd34ce2d8286f17c5a5cc04f2b163
3
+ size 4954909792
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8dbd2b2f1b3de803e428716b6e6e9df248f2f124c66d8279e7699089915c403
3
+ size 2689808472
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6f734c91ccf8cae2cc236e8b4852bd3e1861f545a0f25d5df9db149f0b08fd
3
+ size 4027515024
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff