lthn commited on
Commit
d8d031e
·
verified ·
1 Parent(s): 1f0d924

add nvfp4: config.json

Browse files
Files changed (1) hide show
  1. mlx-nvfp4/config.json +165 -0
mlx-nvfp4/config.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "quantization": {
61
+ "group_size": 16,
62
+ "bits": 4,
63
+ "mode": "nvfp4"
64
+ },
65
+ "quantization_config": {
66
+ "group_size": 16,
67
+ "bits": 4,
68
+ "mode": "nvfp4"
69
+ },
70
+ "text_config": {
71
+ "attention_bias": false,
72
+ "attention_dropout": 0.0,
73
+ "attention_k_eq_v": false,
74
+ "bos_token_id": 2,
75
+ "dtype": "bfloat16",
76
+ "enable_moe_block": false,
77
+ "eos_token_id": 1,
78
+ "expert_intermediate_size": null,
79
+ "final_logit_softcapping": 30.0,
80
+ "global_head_dim": 512,
81
+ "head_dim": 256,
82
+ "hidden_activation": "gelu_pytorch_tanh",
83
+ "hidden_size": 2560,
84
+ "hidden_size_per_layer_input": 256,
85
+ "initializer_range": 0.02,
86
+ "intermediate_size": 10240,
87
+ "layer_types": [
88
+ "sliding_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
+ "sliding_attention",
99
+ "full_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "full_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "full_attention",
112
+ "sliding_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "sliding_attention",
117
+ "full_attention",
118
+ "sliding_attention",
119
+ "sliding_attention",
120
+ "sliding_attention",
121
+ "sliding_attention",
122
+ "sliding_attention",
123
+ "full_attention",
124
+ "sliding_attention",
125
+ "sliding_attention",
126
+ "sliding_attention",
127
+ "sliding_attention",
128
+ "sliding_attention",
129
+ "full_attention"
130
+ ],
131
+ "max_position_embeddings": 131072,
132
+ "model_type": "gemma4_text",
133
+ "num_attention_heads": 8,
134
+ "num_experts": null,
135
+ "num_global_key_value_heads": null,
136
+ "num_hidden_layers": 42,
137
+ "num_key_value_heads": 2,
138
+ "num_kv_shared_layers": 18,
139
+ "pad_token_id": 0,
140
+ "rms_norm_eps": 1e-06,
141
+ "rope_parameters": {
142
+ "full_attention": {
143
+ "partial_rotary_factor": 0.25,
144
+ "rope_theta": 1000000.0,
145
+ "rope_type": "proportional"
146
+ },
147
+ "sliding_attention": {
148
+ "rope_theta": 10000.0,
149
+ "rope_type": "default"
150
+ }
151
+ },
152
+ "sliding_window": 512,
153
+ "tie_word_embeddings": true,
154
+ "top_k_experts": null,
155
+ "use_bidirectional_attention": null,
156
+ "use_cache": true,
157
+ "use_double_wide_mlp": false,
158
+ "vocab_size": 262144,
159
+ "vocab_size_per_layer_input": 262144
160
+ },
161
+ "tie_word_embeddings": true,
162
+ "transformers_version": "5.5.0.dev0",
163
+ "video_token_id": 258884,
164
+ "vision_soft_tokens_per_image": 280
165
+ }