Hugging Face's logo

Shadow0482
/
mythos_full

Any-to-Any
GGUF
gemma4
llama.cpp
vision-language-model
conversational
Model card Files
xet
 Community
Shadow0482 commited on
Commit
a8f0fbd
·
verified ·
1 Parent(s): 082a52f

Trained with Unsloth - config

Browse files
Files changed (1) hide show
  1. config.json +193 -0
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "_name_or_path": "",
7
+ "architectures": null,
8
+ "attention_chunk_size": 12,
9
+ "attention_context_left": 13,
10
+ "attention_context_right": 0,
11
+ "attention_invalid_logits_value": -1000000000.0,
12
+ "attention_logit_cap": 50.0,
13
+ "chunk_size_feed_forward": 0,
14
+ "conv_kernel_size": 5,
15
+ "torch_dtype": "bfloat16",
16
+ "gradient_clipping": 10000000000.0,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "is_encoder_decoder": false,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1
28
+ },
29
+ "model_type": "gemma4_audio",
30
+ "num_attention_heads": 8,
31
+ "num_hidden_layers": 12,
32
+ "output_attentions": false,
33
+ "output_hidden_states": false,
34
+ "output_proj_dims": 1536,
35
+ "problem_type": null,
36
+ "residual_weight": 0.5,
37
+ "return_dict": true,
38
+ "rms_norm_eps": 1e-06,
39
+ "subsampling_conv_channels": [
40
+ 128,
41
+ 32
42
+ ],
43
+ "use_clipped_linears": true
44
+ },
45
+ "audio_token_id": 258881,
46
+ "boa_token_id": 256000,
47
+ "boi_token_id": 255999,
48
+ "torch_dtype": "bfloat16",
49
+ "eoa_token_id": 258883,
50
+ "eoa_token_index": 258883,
51
+ "eoi_token_id": 258882,
52
+ "eos_token_id": [
53
+ 1,
54
+ 106
55
+ ],
56
+ "image_token_id": 258880,
57
+ "initializer_range": 0.02,
58
+ "model_name": "prithivMLmods/gemma-4-E2B-it-Uncensored-MAX",
59
+ "model_type": "gemma4",
60
+ "pad_token_id": 0,
61
+ "text_config": {
62
+ "attention_bias": false,
63
+ "attention_dropout": 0.0,
64
+ "attention_k_eq_v": false,
65
+ "bos_token_id": 2,
66
+ "torch_dtype": "bfloat16",
67
+ "enable_moe_block": false,
68
+ "eos_token_id": 1,
69
+ "expert_intermediate_size": null,
70
+ "final_logit_softcapping": 30.0,
71
+ "global_head_dim": 512,
72
+ "head_dim": 256,
73
+ "hidden_activation": "gelu_pytorch_tanh",
74
+ "hidden_size": 1536,
75
+ "hidden_size_per_layer_input": 256,
76
+ "initializer_range": 0.02,
77
+ "intermediate_size": 6144,
78
+ "layer_types": [
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "full_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "full_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "full_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "sliding_attention",
98
+ "full_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "full_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "full_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "full_attention"
114
+ ],
115
+ "max_position_embeddings": 131072,
116
+ "model_type": "gemma4_text",
117
+ "moe_intermediate_size": null,
118
+ "num_attention_heads": 8,
119
+ "num_experts": null,
120
+ "num_global_key_value_heads": null,
121
+ "num_hidden_layers": 35,
122
+ "num_key_value_heads": 1,
123
+ "num_kv_shared_layers": 20,
124
+ "pad_token_id": 0,
125
+ "rms_norm_eps": 1e-06,
126
+ "rope_parameters": {
127
+ "full_attention": {
128
+ "partial_rotary_factor": 0.25,
129
+ "rope_theta": 1000000.0,
130
+ "rope_type": "proportional"
131
+ },
132
+ "sliding_attention": {
133
+ "rope_theta": 10000.0,
134
+ "rope_type": "default"
135
+ }
136
+ },
137
+ "sliding_window": 512,
138
+ "tie_word_embeddings": true,
139
+ "top_k_experts": null,
140
+ "use_bidirectional_attention": null,
141
+ "use_cache": true,
142
+ "use_double_wide_mlp": true,
143
+ "vocab_size": 262144,
144
+ "vocab_size_per_layer_input": 262144
145
+ },
146
+ "tie_word_embeddings": true,
147
+ "unsloth_version": "2026.4.8",
148
+ "video_token_id": 258884,
149
+ "vision_config": {
150
+ "_name_or_path": "",
151
+ "architectures": null,
152
+ "attention_bias": false,
153
+ "attention_dropout": 0.0,
154
+ "chunk_size_feed_forward": 0,
155
+ "default_output_length": 280,
156
+ "torch_dtype": "bfloat16",
157
+ "global_head_dim": 64,
158
+ "head_dim": 64,
159
+ "hidden_activation": "gelu_pytorch_tanh",
160
+ "hidden_size": 768,
161
+ "id2label": {
162
+ "0": "LABEL_0",
163
+ "1": "LABEL_1"
164
+ },
165
+ "initializer_range": 0.02,
166
+ "intermediate_size": 3072,
167
+ "is_encoder_decoder": false,
168
+ "label2id": {
169
+ "LABEL_0": 0,
170
+ "LABEL_1": 1
171
+ },
172
+ "max_position_embeddings": 131072,
173
+ "model_type": "gemma4_vision",
174
+ "num_attention_heads": 12,
175
+ "num_hidden_layers": 16,
176
+ "num_key_value_heads": 12,
177
+ "output_attentions": false,
178
+ "output_hidden_states": false,
179
+ "patch_size": 16,
180
+ "pooling_kernel_size": 3,
181
+ "position_embedding_size": 10240,
182
+ "problem_type": null,
183
+ "return_dict": true,
184
+ "rms_norm_eps": 1e-06,
185
+ "rope_parameters": {
186
+ "rope_theta": 100.0,
187
+ "rope_type": "default"
188
+ },
189
+ "standardize": false,
190
+ "use_clipped_linears": true
191
+ },
192
+ "vision_soft_tokens_per_image": 280
193
+ }