Hugging Face's logo

lthn
/
lemma-mlx-bf16

Image-Text-to-Text
MLX
Safetensors
gemma4
lemma
bf16
apple-silicon
multimodal
on-device
conversational
Model card Files
xet
 Community
lthn commited on
Commit
bb892c1
·
verified ·
1 Parent(s): eff0cc9

fix(config): sync with upstream Google Gemma 4 day-1 fixes (b446025, b4a6011)

Browse files

- Restore vision_config block; clean eos_token_id to [1, 106]
- Align generation_config.json transformers_version field

Preserves local tokenizer_config.json (model_specific_special_tokens embedded into model during LEK training).

Files changed (1) hide show
  1. config.json +190 -191
config.json CHANGED
@@ -1,198 +1,197 @@
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
- "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
  "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
- 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  ],
57
- "image_token_id": 258880,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  "initializer_range": 0.02,
59
- "model_type": "gemma4",
60
- "text_config": {
61
- "attention_bias": false,
62
- "attention_dropout": 0.0,
63
- "attention_k_eq_v": false,
64
- "bos_token_id": 2,
65
- "dtype": "bfloat16",
66
- "enable_moe_block": false,
67
- "eos_token_id": 1,
68
- "expert_intermediate_size": null,
69
- "final_logit_softcapping": 30.0,
70
- "global_head_dim": 512,
71
- "head_dim": 256,
72
- "hidden_activation": "gelu_pytorch_tanh",
73
- "hidden_size": 2560,
74
- "hidden_size_per_layer_input": 256,
75
- "initializer_range": 0.02,
76
- "intermediate_size": 10240,
77
- "layer_types": [
78
- "sliding_attention",
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
- "sliding_attention",
89
- "full_attention",
90
- "sliding_attention",
91
- "sliding_attention",
92
- "sliding_attention",
93
- "sliding_attention",
94
- "sliding_attention",
95
- "full_attention",
96
- "sliding_attention",
97
- "sliding_attention",
98
- "sliding_attention",
99
- "sliding_attention",
100
- "sliding_attention",
101
- "full_attention",
102
- "sliding_attention",
103
- "sliding_attention",
104
- "sliding_attention",
105
- "sliding_attention",
106
- "sliding_attention",
107
- "full_attention",
108
- "sliding_attention",
109
- "sliding_attention",
110
- "sliding_attention",
111
- "sliding_attention",
112
- "sliding_attention",
113
- "full_attention",
114
- "sliding_attention",
115
- "sliding_attention",
116
- "sliding_attention",
117
- "sliding_attention",
118
- "sliding_attention",
119
- "full_attention"
120
- ],
121
- "max_position_embeddings": 131072,
122
- "model_type": "gemma4_text",
123
- "num_attention_heads": 8,
124
- "num_experts": null,
125
- "num_global_key_value_heads": null,
126
- "num_hidden_layers": 42,
127
- "num_key_value_heads": 2,
128
- "num_kv_shared_layers": 18,
129
- "pad_token_id": 0,
130
- "rms_norm_eps": 1e-06,
131
- "rope_parameters": {
132
- "full_attention": {
133
- "partial_rotary_factor": 0.25,
134
- "rope_theta": 1000000.0,
135
- "rope_type": "proportional"
136
- },
137
- "sliding_attention": {
138
- "rope_theta": 10000.0,
139
- "rope_type": "default"
140
- }
141
- },
142
- "sliding_window": 512,
143
- "tie_word_embeddings": true,
144
- "top_k_experts": null,
145
- "use_bidirectional_attention": null,
146
- "use_cache": true,
147
- "use_double_wide_mlp": false,
148
- "vocab_size": 262144,
149
- "vocab_size_per_layer_input": 262144
150
  },
 
151
  "tie_word_embeddings": true,
152
- "transformers_version": "5.5.0.dev0",
153
- "video_token_id": 258884,
154
- "vision_config": {
155
- "_name_or_path": "",
156
- "architectures": null,
157
- "attention_bias": false,
158
- "attention_dropout": 0.0,
159
- "chunk_size_feed_forward": 0,
160
- "default_output_length": 280,
161
- "dtype": "bfloat16",
162
- "global_head_dim": 64,
163
- "head_dim": 64,
164
- "hidden_activation": "gelu_pytorch_tanh",
165
- "hidden_size": 768,
166
- "id2label": {
167
- "0": "LABEL_0",
168
- "1": "LABEL_1"
169
- },
170
- "initializer_range": 0.02,
171
- "intermediate_size": 3072,
172
- "is_encoder_decoder": false,
173
- "label2id": {
174
- "LABEL_0": 0,
175
- "LABEL_1": 1
176
- },
177
- "max_position_embeddings": 131072,
178
- "model_type": "gemma4_vision",
179
- "num_attention_heads": 12,
180
- "num_hidden_layers": 16,
181
- "num_key_value_heads": 12,
182
- "output_attentions": false,
183
- "output_hidden_states": false,
184
- "patch_size": 16,
185
- "pooling_kernel_size": 3,
186
- "position_embedding_size": 10240,
187
- "problem_type": null,
188
- "return_dict": true,
189
- "rms_norm_eps": 1e-06,
190
- "rope_parameters": {
191
- "rope_theta": 100.0,
192
- "rope_type": "default"
193
- },
194
- "standardize": false,
195
- "use_clipped_linears": true
 
 
 
 
 
196
  },
197
- "vision_soft_tokens_per_image": 280
198
- }
 
 
 
 
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
  "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
+ "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_type": "gemma4",
59
+ "text_config": {
60
+ "attention_bias": false,
61
+ "attention_dropout": 0.0,
62
+ "attention_k_eq_v": false,
63
+ "bos_token_id": 2,
64
+ "dtype": "bfloat16",
65
+ "enable_moe_block": false,
66
+ "eos_token_id": 1,
67
+ "expert_intermediate_size": null,
68
+ "final_logit_softcapping": 30.0,
69
+ "global_head_dim": 512,
70
+ "head_dim": 256,
71
+ "hidden_activation": "gelu_pytorch_tanh",
72
+ "hidden_size": 2560,
73
+ "hidden_size_per_layer_input": 256,
74
  "initializer_range": 0.02,
75
+ "intermediate_size": 10240,
76
+ "layer_types": [
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "full_attention",
83
+ "sliding_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
+ "sliding_attention",
94
+ "full_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "full_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "full_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "full_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "sliding_attention",
117
+ "sliding_attention",
118
+ "full_attention"
119
+ ],
120
+ "max_position_embeddings": 131072,
121
+ "model_type": "gemma4_text",
122
+ "num_attention_heads": 8,
123
+ "num_experts": null,
124
+ "num_global_key_value_heads": null,
125
+ "num_hidden_layers": 42,
126
+ "num_key_value_heads": 2,
127
+ "num_kv_shared_layers": 18,
128
+ "pad_token_id": 0,
129
+ "rms_norm_eps": 1e-06,
130
+ "rope_parameters": {
131
+ "full_attention": {
132
+ "partial_rotary_factor": 0.25,
133
+ "rope_theta": 1000000.0,
134
+ "rope_type": "proportional"
135
+ },
136
+ "sliding_attention": {
137
+ "rope_theta": 10000.0,
138
+ "rope_type": "default"
139
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  },
141
+ "sliding_window": 512,
142
  "tie_word_embeddings": true,
143
+ "top_k_experts": null,
144
+ "use_bidirectional_attention": null,
145
+ "use_cache": true,
146
+ "use_double_wide_mlp": false,
147
+ "vocab_size": 262144,
148
+ "vocab_size_per_layer_input": 262144
149
+ },
150
+ "tie_word_embeddings": true,
151
+ "transformers_version": "5.5.0.dev0",
152
+ "video_token_id": 258884,
153
+ "vision_config": {
154
+ "_name_or_path": "",
155
+ "architectures": null,
156
+ "attention_bias": false,
157
+ "attention_dropout": 0.0,
158
+ "chunk_size_feed_forward": 0,
159
+ "default_output_length": 280,
160
+ "dtype": "bfloat16",
161
+ "global_head_dim": 64,
162
+ "head_dim": 64,
163
+ "hidden_activation": "gelu_pytorch_tanh",
164
+ "hidden_size": 768,
165
+ "id2label": {
166
+ "0": "LABEL_0",
167
+ "1": "LABEL_1"
168
+ },
169
+ "initializer_range": 0.02,
170
+ "intermediate_size": 3072,
171
+ "is_encoder_decoder": false,
172
+ "label2id": {
173
+ "LABEL_0": 0,
174
+ "LABEL_1": 1
175
+ },
176
+ "max_position_embeddings": 131072,
177
+ "model_type": "gemma4_vision",
178
+ "num_attention_heads": 12,
179
+ "num_hidden_layers": 16,
180
+ "num_key_value_heads": 12,
181
+ "output_attentions": false,
182
+ "output_hidden_states": false,
183
+ "patch_size": 16,
184
+ "pooling_kernel_size": 3,
185
+ "position_embedding_size": 10240,
186
+ "problem_type": null,
187
+ "return_dict": true,
188
+ "rms_norm_eps": 1e-06,
189
+ "rope_parameters": {
190
+ "rope_theta": 100.0,
191
+ "rope_type": "default"
192
  },
193
+ "standardize": false,
194
+ "use_clipped_linears": true
195
+ },
196
+ "vision_soft_tokens_per_image": 280
197
+ }