Hugging Face's logo

lthn
/
lemrd-mlx

Image-Text-to-Text
MLX
Safetensors
gemma4
lemma
4bit
apple-silicon
multimodal
on-device
conversational
4-bit precision
Model card Files
xet
 Community
lthn commited on
Commit
fe264d9
·
verified ·
1 Parent(s): 5285556

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +137 -174
config.json CHANGED
@@ -1,181 +1,144 @@
1
  {
2
- "architectures": [
3
- "Gemma4ForConditionalGeneration"
4
- ],
5
- "audio_config": null,
6
- "audio_token_id": 258881,
7
- "boa_token_id": 256000,
8
- "boi_token_id": 255999,
9
- "dtype": "bfloat16",
10
- "eoa_token_id": 258883,
11
- "eoa_token_index": 258883,
12
- "eoi_token_id": 258882,
13
- "eos_token_id": [
14
- 1,
15
- 106
16
- ],
17
- "image_token_id": 258880,
18
- "initializer_range": 0.02,
19
- "model_type": "gemma4",
20
- "text_config": {
21
- "attention_bias": false,
22
- "attention_dropout": 0.0,
23
- "attention_k_eq_v": true,
24
- "bos_token_id": 2,
25
- "dtype": "bfloat16",
26
- "enable_moe_block": false,
27
- "eos_token_id": 1,
28
- "expert_intermediate_size": null,
29
- "final_logit_softcapping": 30.0,
30
- "global_head_dim": 512,
31
- "head_dim": 256,
32
- "hidden_activation": "gelu_pytorch_tanh",
33
- "hidden_size": 5376,
34
- "hidden_size_per_layer_input": 0,
35
- "initializer_range": 0.02,
36
- "intermediate_size": 21504,
37
- "layer_types": [
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
- "sliding_attention",
67
- "full_attention",
68
- "sliding_attention",
69
- "sliding_attention",
70
- "sliding_attention",
71
- "sliding_attention",
72
- "sliding_attention",
73
- "full_attention",
74
- "sliding_attention",
75
- "sliding_attention",
76
- "sliding_attention",
77
- "sliding_attention",
78
- "sliding_attention",
79
- "full_attention",
80
- "sliding_attention",
81
- "sliding_attention",
82
- "sliding_attention",
83
- "sliding_attention",
84
- "sliding_attention",
85
- "full_attention",
86
- "sliding_attention",
87
- "sliding_attention",
88
- "sliding_attention",
89
- "sliding_attention",
90
- "sliding_attention",
91
- "full_attention",
92
- "sliding_attention",
93
- "sliding_attention",
94
- "sliding_attention",
95
- "sliding_attention",
96
- "sliding_attention",
97
- "full_attention"
98
  ],
99
- "max_position_embeddings": 262144,
100
- "model_type": "gemma4_text",
101
- "num_attention_heads": 32,
102
- "num_experts": null,
103
- "num_global_key_value_heads": 4,
104
- "num_hidden_layers": 60,
105
- "num_key_value_heads": 16,
106
- "num_kv_shared_layers": 0,
107
- "pad_token_id": 0,
108
- "rms_norm_eps": 1e-06,
109
- "rope_parameters": {
110
- "full_attention": {
111
- "partial_rotary_factor": 0.25,
112
- "rope_theta": 1000000.0,
113
- "rope_type": "proportional"
114
- },
115
- "sliding_attention": {
116
- "rope_theta": 10000.0,
117
- "rope_type": "default"
118
- }
119
- },
120
- "sliding_window": 1024,
121
- "tie_word_embeddings": true,
122
- "top_k_experts": null,
123
- "use_bidirectional_attention": "vision",
124
- "use_cache": true,
125
- "use_double_wide_mlp": false,
126
- "vocab_size": 262144,
127
- "vocab_size_per_layer_input": 262144
128
- },
129
- "tie_word_embeddings": true,
130
- "transformers_version": "5.5.0.dev0",
131
- "video_token_id": 258884,
132
- "vision_config": {
133
- "_name_or_path": "",
134
- "architectures": null,
135
- "attention_bias": false,
136
- "attention_dropout": 0.0,
137
- "chunk_size_feed_forward": 0,
138
- "default_output_length": 280,
139
  "dtype": "bfloat16",
140
- "global_head_dim": 72,
141
- "head_dim": 72,
142
- "hidden_activation": "gelu_pytorch_tanh",
143
- "hidden_size": 1152,
144
- "id2label": {
145
- "0": "LABEL_0",
146
- "1": "LABEL_1"
147
- },
 
148
  "initializer_range": 0.02,
149
- "intermediate_size": 4304,
150
- "is_encoder_decoder": false,
151
- "label2id": {
152
- "LABEL_0": 0,
153
- "LABEL_1": 1
154
  },
155
- "max_position_embeddings": 131072,
156
- "model_type": "gemma4_vision",
157
- "num_attention_heads": 16,
158
- "num_hidden_layers": 27,
159
- "num_key_value_heads": 16,
160
- "output_attentions": false,
161
- "output_hidden_states": false,
162
- "patch_size": 16,
163
- "pooling_kernel_size": 3,
164
- "position_embedding_size": 10240,
165
- "problem_type": null,
166
- "return_dict": true,
167
- "rms_norm_eps": 1e-06,
168
- "rope_parameters": {
169
- "rope_theta": 100.0,
170
- "rope_type": "default"
171
  },
172
- "standardize": true,
173
- "use_clipped_linears": false
174
- },
175
- "vision_soft_tokens_per_image": 280,
176
- "quantization_config": {
177
- "bits": 4,
178
- "group_size": 64,
179
- "mode": "affine"
180
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
181
  }
 
1
  {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
+ "audio_config": null,
6
+ "audio_token_id": 258881,
7
+ "boa_token_id": 256000,
8
+ "boi_token_id": 255999,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "dtype": "bfloat16",
10
+ "eoa_token_id": 258883,
11
+ "eoa_token_index": 258883,
12
+ "eoi_token_id": 258882,
13
+ "eos_token_id": [
14
+ 1,
15
+ 106,
16
+ 50
17
+ ],
18
+ "image_token_id": 258880,
19
  "initializer_range": 0.02,
20
+ "model_type": "gemma4",
21
+ "quantization": {
22
+ "group_size": 64,
23
+ "bits": 4,
24
+ "mode": "affine"
25
  },
26
+ "quantization_config": {
27
+ "group_size": 64,
28
+ "bits": 4,
29
+ "mode": "affine"
 
 
 
 
 
 
 
 
 
 
 
 
30
  },
31
+ "text_config": {
32
+ "attention_bias": false,
33
+ "attention_dropout": 0.0,
34
+ "attention_k_eq_v": true,
35
+ "bos_token_id": 2,
36
+ "dtype": "bfloat16",
37
+ "enable_moe_block": false,
38
+ "eos_token_id": 1,
39
+ "expert_intermediate_size": null,
40
+ "final_logit_softcapping": 30.0,
41
+ "global_head_dim": 512,
42
+ "head_dim": 256,
43
+ "hidden_activation": "gelu_pytorch_tanh",
44
+ "hidden_size": 5376,
45
+ "hidden_size_per_layer_input": 0,
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 21504,
48
+ "layer_types": [
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "full_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "full_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "full_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "full_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "full_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "full_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "full_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "full_attention"
109
+ ],
110
+ "max_position_embeddings": 262144,
111
+ "model_type": "gemma4_text",
112
+ "num_attention_heads": 32,
113
+ "num_experts": null,
114
+ "num_global_key_value_heads": 4,
115
+ "num_hidden_layers": 60,
116
+ "num_key_value_heads": 16,
117
+ "num_kv_shared_layers": 0,
118
+ "pad_token_id": 0,
119
+ "rms_norm_eps": 1e-06,
120
+ "rope_parameters": {
121
+ "full_attention": {
122
+ "partial_rotary_factor": 0.25,
123
+ "rope_theta": 1000000.0,
124
+ "rope_type": "proportional"
125
+ },
126
+ "sliding_attention": {
127
+ "rope_theta": 10000.0,
128
+ "rope_type": "default"
129
+ }
130
+ },
131
+ "sliding_window": 1024,
132
+ "tie_word_embeddings": true,
133
+ "top_k_experts": null,
134
+ "use_bidirectional_attention": "vision",
135
+ "use_cache": true,
136
+ "use_double_wide_mlp": false,
137
+ "vocab_size": 262144,
138
+ "vocab_size_per_layer_input": 262144
139
+ },
140
+ "tie_word_embeddings": true,
141
+ "transformers_version": "5.5.0.dev0",
142
+ "video_token_id": 258884,
143
+ "vision_soft_tokens_per_image": 280
144
  }