Hugging Face's logo

lthn
/
lemrd-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
4c097f2
·
verified ·
1 Parent(s): 9566467

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +137 -128
config.json CHANGED
@@ -1,134 +1,143 @@
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
- "text_config": {
22
- "attention_bias": false,
23
- "attention_dropout": 0.0,
24
- "attention_k_eq_v": true,
25
- "bos_token_id": 2,
26
- "dtype": "bfloat16",
27
- "enable_moe_block": false,
28
- "eos_token_id": 1,
29
- "expert_intermediate_size": null,
30
- "final_logit_softcapping": 30.0,
31
- "global_head_dim": 512,
32
- "head_dim": 256,
33
- "hidden_activation": "gelu_pytorch_tanh",
34
- "hidden_size": 5376,
35
- "hidden_size_per_layer_input": 0,
36
- "initializer_range": 0.02,
37
- "intermediate_size": 21504,
38
- "layer_types": [
39
- "sliding_attention",
40
- "sliding_attention",
41
- "sliding_attention",
42
- "sliding_attention",
43
- "sliding_attention",
44
- "full_attention",
45
- "sliding_attention",
46
- "sliding_attention",
47
- "sliding_attention",
48
- "sliding_attention",
49
- "sliding_attention",
50
- "full_attention",
51
- "sliding_attention",
52
- "sliding_attention",
53
- "sliding_attention",
54
- "sliding_attention",
55
- "sliding_attention",
56
- "full_attention",
57
- "sliding_attention",
58
- "sliding_attention",
59
- "sliding_attention",
60
- "sliding_attention",
61
- "sliding_attention",
62
- "full_attention",
63
- "sliding_attention",
64
- "sliding_attention",
65
- "sliding_attention",
66
- "sliding_attention",
67
- "sliding_attention",
68
- "full_attention",
69
- "sliding_attention",
70
- "sliding_attention",
71
- "sliding_attention",
72
- "sliding_attention",
73
- "sliding_attention",
74
- "full_attention",
75
- "sliding_attention",
76
- "sliding_attention",
77
- "sliding_attention",
78
- "sliding_attention",
79
- "sliding_attention",
80
- "full_attention",
81
- "sliding_attention",
82
- "sliding_attention",
83
- "sliding_attention",
84
- "sliding_attention",
85
- "sliding_attention",
86
- "full_attention",
87
- "sliding_attention",
88
- "sliding_attention",
89
- "sliding_attention",
90
- "sliding_attention",
91
- "sliding_attention",
92
- "full_attention",
93
- "sliding_attention",
94
- "sliding_attention",
95
- "sliding_attention",
96
- "sliding_attention",
97
- "sliding_attention",
98
- "full_attention"
99
- ],
100
- "max_position_embeddings": 262144,
101
- "model_type": "gemma4_text",
102
- "num_attention_heads": 32,
103
- "num_experts": null,
104
- "num_global_key_value_heads": 4,
105
- "num_hidden_layers": 60,
106
- "num_key_value_heads": 16,
107
- "num_kv_shared_layers": 0,
108
- "pad_token_id": 0,
109
- "rms_norm_eps": 1e-06,
110
- "rope_parameters": {
111
- "full_attention": {
112
- "partial_rotary_factor": 0.25,
113
- "rope_theta": 1000000.0,
114
- "rope_type": "proportional"
115
- },
116
- "sliding_attention": {
117
- "rope_theta": 10000.0,
118
- "rope_type": "default"
119
- }
120
- },
121
- "sliding_window": 1024,
122
- "tie_word_embeddings": true,
123
- "top_k_experts": null,
124
- "use_bidirectional_attention": "vision",
125
- "use_cache": true,
126
- "use_double_wide_mlp": false,
127
- "vocab_size": 262144,
128
- "vocab_size_per_layer_input": 262144
129
  },
 
130
  "tie_word_embeddings": true,
131
- "transformers_version": "5.5.0.dev0",
132
- "video_token_id": 258884,
133
- "vision_soft_tokens_per_image": 280
 
 
 
 
 
 
 
 
134
  }
 
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
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 4,
23
+ "mode": "affine"
24
+ },
25
+ "quantization_config": {
26
+ "group_size": 64,
27
+ "bits": 4,
28
+ "mode": "affine"
29
+ },
30
+ "text_config": {
31
+ "attention_bias": false,
32
+ "attention_dropout": 0.0,
33
+ "attention_k_eq_v": true,
34
+ "bos_token_id": 2,
35
  "dtype": "bfloat16",
36
+ "enable_moe_block": false,
37
+ "eos_token_id": 1,
38
+ "expert_intermediate_size": null,
39
+ "final_logit_softcapping": 30.0,
40
+ "global_head_dim": 512,
41
+ "head_dim": 256,
42
+ "hidden_activation": "gelu_pytorch_tanh",
43
+ "hidden_size": 5376,
44
+ "hidden_size_per_layer_input": 0,
45
  "initializer_range": 0.02,
46
+ "intermediate_size": 21504,
47
+ "layer_types": [
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "full_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "full_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention",
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
+ ],
109
+ "max_position_embeddings": 262144,
110
+ "model_type": "gemma4_text",
111
+ "num_attention_heads": 32,
112
+ "num_experts": null,
113
+ "num_global_key_value_heads": 4,
114
+ "num_hidden_layers": 60,
115
+ "num_key_value_heads": 16,
116
+ "num_kv_shared_layers": 0,
117
+ "pad_token_id": 0,
118
+ "rms_norm_eps": 1e-06,
119
+ "rope_parameters": {
120
+ "full_attention": {
121
+ "partial_rotary_factor": 0.25,
122
+ "rope_theta": 1000000.0,
123
+ "rope_type": "proportional"
124
+ },
125
+ "sliding_attention": {
126
+ "rope_theta": 10000.0,
127
+ "rope_type": "default"
128
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
  },
130
+ "sliding_window": 1024,
131
  "tie_word_embeddings": true,
132
+ "top_k_experts": null,
133
+ "use_bidirectional_attention": "vision",
134
+ "use_cache": true,
135
+ "use_double_wide_mlp": false,
136
+ "vocab_size": 262144,
137
+ "vocab_size_per_layer_input": 262144
138
+ },
139
+ "tie_word_embeddings": true,
140
+ "transformers_version": "5.5.0.dev0",
141
+ "video_token_id": 258884,
142
+ "vision_soft_tokens_per_image": 280
143
  }