Hugging Face's logo

Json31
/
model

GGUF
gemma3
llama.cpp
unsloth
vision-language-model
Model card Files
xet
Community
Json31 commited on
Commit
9e8522f
·
verified ·
1 Parent(s): 48f6a83

Trained with Unsloth - config

Browse files
Files changed (1) hide show
  1. config.json +102 -69
config.json CHANGED
@@ -1,80 +1,113 @@
1
  {
2
  "architectures": [
3
- "Gemma2ForCausalLM"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": 50.0,
8
  "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
  "torch_dtype": "bfloat16",
11
- "eos_token_id": 1,
12
- "final_logit_softcapping": 30.0,
13
- "head_dim": 256,
14
- "hidden_act": "gelu_pytorch_tanh",
15
- "hidden_activation": "gelu_pytorch_tanh",
16
- "hidden_size": 3584,
17
  "initializer_range": 0.02,
18
- "intermediate_size": 14336,
19
- "layer_types": [
20
- "sliding_attention",
21
- "full_attention",
22
- "sliding_attention",
23
- "full_attention",
24
- "sliding_attention",
25
- "full_attention",
26
- "sliding_attention",
27
- "full_attention",
28
- "sliding_attention",
29
- "full_attention",
30
- "sliding_attention",
31
- "full_attention",
32
- "sliding_attention",
33
- "full_attention",
34
- "sliding_attention",
35
- "full_attention",
36
- "sliding_attention",
37
- "full_attention",
38
- "sliding_attention",
39
- "full_attention",
40
- "sliding_attention",
41
- "full_attention",
42
- "sliding_attention",
43
- "full_attention",
44
- "sliding_attention",
45
- "full_attention",
46
- "sliding_attention",
47
- "full_attention",
48
- "sliding_attention",
49
- "full_attention",
50
- "sliding_attention",
51
- "full_attention",
52
- "sliding_attention",
53
- "full_attention",
54
- "sliding_attention",
55
- "full_attention",
56
- "sliding_attention",
57
- "full_attention",
58
- "sliding_attention",
59
- "full_attention",
60
- "sliding_attention",
61
- "full_attention"
62
- ],
63
- "max_position_embeddings": 8192,
64
- "model_type": "gemma2",
65
- "num_attention_heads": 16,
66
- "num_hidden_layers": 42,
67
- "num_key_value_heads": 8,
68
  "pad_token_id": 0,
69
- "query_pre_attn_scalar": 256,
70
- "rms_norm_eps": 1e-06,
71
- "rope_scaling": null,
72
- "rope_theta": 10000.0,
73
- "sliding_window": 4096,
74
- "sliding_window_size": 4096,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  "transformers_version": "4.56.2",
76
  "unsloth_fixed": true,
77
  "unsloth_version": "2025.10.8",
78
- "use_cache": true,
79
- "vocab_size": 256000
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  }
 
1
  {
2
  "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
  ],
5
+ "boi_token_index": 255999,
 
 
6
  "bos_token_id": 2,
 
7
  "torch_dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "image_token_index": 262144,
 
 
 
11
  "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "pad_token_id": 0,
15
+ "text_config": {
16
+ "_sliding_window_pattern": 6,
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_logit_softcapping": null,
20
+ "cache_implementation": "hybrid",
21
+ "torch_dtype": "bfloat16",
22
+ "final_logit_softcapping": null,
23
+ "head_dim": 256,
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_size": 3840,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 15360,
28
+ "layer_types": [
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
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "full_attention"
77
+ ],
78
+ "max_position_embeddings": 131072,
79
+ "model_type": "gemma3_text",
80
+ "num_attention_heads": 16,
81
+ "num_hidden_layers": 48,
82
+ "num_key_value_heads": 8,
83
+ "query_pre_attn_scalar": 256,
84
+ "rms_norm_eps": 1e-06,
85
+ "rope_local_base_freq": 10000.0,
86
+ "rope_scaling": {
87
+ "factor": 8.0,
88
+ "rope_type": "linear"
89
+ },
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": 1024,
92
+ "use_cache": true,
93
+ "vocab_size": 262208
94
+ },
95
  "transformers_version": "4.56.2",
96
  "unsloth_fixed": true,
97
  "unsloth_version": "2025.10.8",
98
+ "vision_config": {
99
+ "attention_dropout": 0.0,
100
+ "torch_dtype": "bfloat16",
101
+ "hidden_act": "gelu_pytorch_tanh",
102
+ "hidden_size": 1152,
103
+ "image_size": 896,
104
+ "intermediate_size": 4304,
105
+ "layer_norm_eps": 1e-06,
106
+ "model_type": "siglip_vision_model",
107
+ "num_attention_heads": 16,
108
+ "num_channels": 3,
109
+ "num_hidden_layers": 27,
110
+ "patch_size": 14,
111
+ "vision_use_head": false
112
+ }
113
  }