Hugging Face's logo

corruptbytes
/
North-Mini-Code-1.0-oQ6

Safetensors
cohere2_moe
6-bit
Model card Files
xet
 Community
North-Mini-Code-1.0-oQ6
File size: 5,522 Bytes
58f9f83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
{
  "architectures": [
    "Cohere2MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "dtype": "bfloat16",
  "eos_token_id": 255001,
  "expert_selection_fn": "sigmoid",
  "first_k_dense_replace": 1,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 768,
  "layer_norm_eps": 1e-05,
  "layer_types": [
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "logit_scale": 1.0,
  "max_position_embeddings": 500000,
  "model_type": "cohere2_moe",
  "norm_topk_prob": false,
  "num_attention_heads": 32,
  "num_experts": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 49,
  "num_key_value_heads": 4,
  "num_shared_experts": 0,
  "pad_token_id": 0,
  "prefix_dense_intermediate_size": 3072,
  "prefix_dense_sliding_window_pattern": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 50000,
  "shared_expert_combination_strategy": "average",
  "sliding_window": 4096,
  "transformers_version": "5.8.0",
  "use_cache": true,
  "use_gated_activation": true,
  "use_parallel_block": true,
  "use_parallel_embedding": false,
  "use_qk_norm": false,
  "vocab_size": 262144,
  "quantization": {
    "group_size": 64,
    "bits": 6,
    "mode": "affine",
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    }
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 6,
    "mode": "affine",
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.0.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    },
    "language_model.model.layers.24.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64,
      "mode": "affine"
    }
  }
}