Hugging Face's logo

foxespri
/
ds

GGUF
gemma3
llama.cpp
unsloth
vision-language-model
conversational
Model card Files
xet
 Community
foxespri commited on
Commit
f36149c
·
verified ·
1 Parent(s): c808f54

Trained with Unsloth - config

Browse files
Files changed (1) hide show
  1. config.json +112 -0
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_name": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
14
+ "model_type": "gemma3",
15
+ "pad_token_id": 0,
16
+ "text_config": {
17
+ "_sliding_window_pattern": 6,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "bos_token_id": 2,
22
+ "cache_implementation": "hybrid",
23
+ "torch_dtype": "bfloat16",
24
+ "eos_token_id": 1,
25
+ "final_logit_softcapping": null,
26
+ "head_dim": 256,
27
+ "hidden_activation": "gelu_pytorch_tanh",
28
+ "hidden_size": 2560,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 10240,
31
+ "layer_types": [
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention"
66
+ ],
67
+ "max_position_embeddings": 131072,
68
+ "model_type": "gemma3_text",
69
+ "num_attention_heads": 8,
70
+ "num_hidden_layers": 34,
71
+ "num_key_value_heads": 4,
72
+ "pad_token_id": 0,
73
+ "query_pre_attn_scalar": 256,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_parameters": {
76
+ "full_attention": {
77
+ "factor": 8.0,
78
+ "rope_theta": 1000000.0,
79
+ "rope_type": "linear"
80
+ },
81
+ "sliding_attention": {
82
+ "rope_theta": 10000.0,
83
+ "rope_type": "default"
84
+ }
85
+ },
86
+ "sliding_window": 1024,
87
+ "sliding_window_pattern": 6,
88
+ "tie_word_embeddings": true,
89
+ "use_bidirectional_attention": false,
90
+ "use_cache": true,
91
+ "vocab_size": 262208
92
+ },
93
+ "tie_word_embeddings": true,
94
+ "unsloth_fixed": true,
95
+ "unsloth_version": "2026.3.3",
96
+ "use_cache": false,
97
+ "vision_config": {
98
+ "attention_dropout": 0.0,
99
+ "torch_dtype": "bfloat16",
100
+ "hidden_act": "gelu_pytorch_tanh",
101
+ "hidden_size": 1152,
102
+ "image_size": 896,
103
+ "intermediate_size": 4304,
104
+ "layer_norm_eps": 1e-06,
105
+ "model_type": "siglip_vision_model",
106
+ "num_attention_heads": 16,
107
+ "num_channels": 3,
108
+ "num_hidden_layers": 27,
109
+ "patch_size": 14,
110
+ "vision_use_head": false
111
+ }
112
+ }