Hugging Face's logo

mcrovero
/
gemma-3-12b-it-custom-merged-4

Image-Text-to-Text
Transformers
English
gemma3
text-generation-inference
unsloth
conversational
Model card Files Community
mcrovero commited on
Commit
c5f8eba
·
verified ·
1 Parent(s): 24c53f8

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +54 -29
config.json CHANGED
@@ -1,37 +1,62 @@
1
  {
2
  "architectures": [
3
- "Gemma3ForCausalLM"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
  "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 3840,
15
  "initializer_range": 0.02,
16
- "intermediate_size": 15360,
17
- "max_position_embeddings": 131072,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 16,
20
- "num_hidden_layers": 48,
21
- "num_key_value_heads": 8,
22
  "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000.0,
26
- "rope_scaling": {
27
- "factor": 8.0,
28
- "rope_type": "linear"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  },
30
- "rope_theta": 1000000.0,
31
- "sliding_window": 1024,
32
- "sliding_window_pattern": 6,
33
  "torch_dtype": "bfloat16",
34
- "transformers_version": "4.50.0.dev0",
35
- "use_cache": true,
36
- "vocab_size": 262208
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
  "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
  ],
5
+ "boi_token_index": 255999,
 
 
6
  "bos_token_id": 2,
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": 106,
9
+ "image_token_index": 262144,
 
 
 
10
  "initializer_range": 0.02,
11
+ "mm_tokens_per_image": 256,
12
+ "model_type": "gemma3",
 
 
 
 
13
  "pad_token_id": 0,
14
+ "text_config": {
15
+ "attention_bias": false,
16
+ "attention_dropout": 0.0,
17
+ "attn_logit_softcapping": null,
18
+ "cache_implementation": "hybrid",
19
+ "final_logit_softcapping": null,
20
+ "head_dim": 256,
21
+ "hidden_activation": "gelu_pytorch_tanh",
22
+ "hidden_size": 3840,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 15360,
25
+ "max_position_embeddings": 131072,
26
+ "model_type": "gemma3_text",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 48,
29
+ "num_key_value_heads": 8,
30
+ "query_pre_attn_scalar": 256,
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_local_base_freq": 10000.0,
33
+ "rope_scaling": {
34
+ "factor": 8.0,
35
+ "rope_type": "linear"
36
+ },
37
+ "rope_theta": 1000000.0,
38
+ "sliding_window": 1024,
39
+ "sliding_window_pattern": 6,
40
+ "torch_dtype": "bfloat16",
41
+ "use_cache": true,
42
+ "vocab_size": 262208
43
  },
 
 
 
44
  "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.51.0",
46
+ "unsloth_fixed": true,
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": "bfloat16",
60
+ "vision_use_head": false
61
+ }
62
+ }