Hugging Face's logo

0xSero
/
GLM-5.2-504B-W4A16

Text Generation
Safetensors
glm_moe_dsa
Mixture of Experts
reap
pruning
expert-pruning
router-kd
nvfp4
glm
glm-5.2
conversational
4-bit precision
auto-round
Model card Files
xet
 Community
1
0xSero commited on
Commit
2eb34c3
·
verified ·
1 Parent(s): 8748896

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +119 -0
  3. config.json +449 -0
  4. model-00001-of-00049.safetensors +3 -0
  5. model-00002-of-00049.safetensors +3 -0
  6. model-00003-of-00049.safetensors +3 -0
  7. model-00004-of-00049.safetensors +3 -0
  8. model-00005-of-00049.safetensors +3 -0
  9. model-00006-of-00049.safetensors +3 -0
  10. model-00007-of-00049.safetensors +3 -0
  11. model-00008-of-00049.safetensors +3 -0
  12. model-00009-of-00049.safetensors +3 -0
  13. model-00010-of-00049.safetensors +3 -0
  14. model-00011-of-00049.safetensors +3 -0
  15. model-00012-of-00049.safetensors +3 -0
  16. model-00013-of-00049.safetensors +3 -0
  17. model-00014-of-00049.safetensors +3 -0
  18. model-00015-of-00049.safetensors +3 -0
  19. model-00016-of-00049.safetensors +3 -0
  20. model-00017-of-00049.safetensors +3 -0
  21. model-00018-of-00049.safetensors +3 -0
  22. model-00019-of-00049.safetensors +3 -0
  23. model-00020-of-00049.safetensors +3 -0
  24. model-00021-of-00049.safetensors +3 -0
  25. model-00022-of-00049.safetensors +3 -0
  26. model-00023-of-00049.safetensors +3 -0
  27. model-00024-of-00049.safetensors +3 -0
  28. model-00025-of-00049.safetensors +3 -0
  29. model-00026-of-00049.safetensors +3 -0
  30. model-00027-of-00049.safetensors +3 -0
  31. model-00028-of-00049.safetensors +3 -0
  32. model-00029-of-00049.safetensors +3 -0
  33. model-00030-of-00049.safetensors +3 -0
  34. model-00031-of-00049.safetensors +3 -0
  35. model-00032-of-00049.safetensors +3 -0
  36. model-00033-of-00049.safetensors +3 -0
  37. model-00034-of-00049.safetensors +3 -0
  38. model-00035-of-00049.safetensors +3 -0
  39. model-00036-of-00049.safetensors +3 -0
  40. model-00037-of-00049.safetensors +3 -0
  41. model-00038-of-00049.safetensors +3 -0
  42. model-00039-of-00049.safetensors +3 -0
  43. model-00040-of-00049.safetensors +3 -0
  44. model-00041-of-00049.safetensors +3 -0
  45. model-00042-of-00049.safetensors +3 -0
  46. model-00043-of-00049.safetensors +3 -0
  47. model-00044-of-00049.safetensors +3 -0
  48. model-00045-of-00049.safetensors +3 -0
  49. model-00046-of-00049.safetensors +3 -0
  50. model-00047-of-00049.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%}
3
+ {%- if (enable_thinking is not defined or enable_thinking) and effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
4
+ {%- if tools -%}
5
+ {%- macro tool_to_json(tool) -%}
6
+ {%- set ns_tool = namespace(first=true) -%}
7
+ {{ '{' -}}
8
+ {%- for k, v in tool.items() -%}
9
+ {%- if k != 'defer_loading' and k != 'strict' -%}
10
+ {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
11
+ {%- set ns_tool.first = false -%}
12
+ "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
13
+ {%- endif -%}
14
+ {%- endfor -%}
15
+ {{- '}' -}}
16
+ {%- endmacro -%}
17
+ <|system|>
18
+ # Tools
19
+
20
+ You may call one or more functions to assist with the user query.
21
+
22
+ You are provided with function signatures within <tools></tools> XML tags:
23
+ <tools>
24
+ {% for tool in tools %}
25
+ {%- if 'function' in tool -%}
26
+ {%- set tool = tool['function'] -%}
27
+ {%- endif -%}
28
+ {% if tool.defer_loading is not defined or not tool.defer_loading %}
29
+ {{ tool_to_json(tool) }}
30
+ {% endif %}
31
+ {% endfor %}
32
+ </tools>
33
+
34
+ For each function call, output the function name and arguments within the following XML format:
35
+ <tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
36
+ {%- macro visible_text(content) -%}
37
+ {%- if content is string -%}
38
+ {{- content }}
39
+ {%- elif content is iterable and content is not mapping -%}
40
+ {%- for item in content -%}
41
+ {%- if item is mapping and item.type == 'text' -%}
42
+ {{- item.text }}
43
+ {%- elif item is string -%}
44
+ {{- item }}
45
+ {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
46
+ {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
47
+ {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
48
+ {%- endif -%}
49
+ {%- endfor -%}
50
+ {%- else -%}
51
+ {{- content }}
52
+ {%- endif -%}
53
+ {%- endmacro -%}
54
+ {%- set ns = namespace(last_user_index=-1) -%}
55
+ {%- for m in messages %}
56
+ {%- if m.role == 'user' %}
57
+ {%- set ns.last_user_index = loop.index0 -%}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {%- for m in messages -%}
61
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
62
+ {%- elif m.role == 'assistant' -%}
63
+ <|assistant|>
64
+ {%- set content = visible_text(m.content) %}
65
+ {%- if m.reasoning_content is string %}
66
+ {%- set reasoning_content = m.reasoning_content %}
67
+ {%- elif '</think>' in content %}
68
+ {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
69
+ {%- set content = content.split('</think>')[-1] %}
70
+ {%- endif %}
71
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
72
+ {{ '<think>' + reasoning_content + '</think>'}}
73
+ {%- else -%}
74
+ {{ '<think></think>' }}
75
+ {%- endif -%}
76
+ {%- if content.strip() -%}
77
+ {{ content.strip() }}
78
+ {%- endif -%}
79
+ {% if m.tool_calls %}
80
+ {% for tc in m.tool_calls %}
81
+ {%- if tc.function %}
82
+ {%- set tc = tc.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>' + tc.name -}}
85
+ {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
86
+ {% endif %}
87
+ {%- elif m.role == 'tool' -%}
88
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
89
+ {{- '<|observation|>' -}}
90
+ {%- endif %}
91
+ {%- if m.content is string -%}
92
+ {{- '<tool_response>' + m.content + '</tool_response>' -}}
93
+ {%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == "tool_reference" -%}
94
+ {{- '<tool_response><tools>\n' -}}
95
+ {% for tr in m.content %}
96
+ {%- for tool in tools -%}
97
+ {%- if 'function' in tool -%}
98
+ {%- set tool = tool['function'] -%}
99
+ {%- endif -%}
100
+ {%- if tool.name == tr.name -%}
101
+ {{- tool_to_json(tool) + '\n' -}}
102
+ {%- endif -%}
103
+ {%- endfor -%}
104
+ {%- endfor -%}
105
+ {{- '</tools></tool_response>' -}}
106
+ {%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%}
107
+ {%- for tr in m.content -%}
108
+ {{- '<tool_response>' + tr.output + '</tool_response>' -}}
109
+ {%- endfor -%}
110
+ {%- else -%}
111
+ {{- '<tool_response>' + visible_text(m.content) + '</tool_response>' -}}
112
+ {% endif -%}
113
+ {%- elif m.role == 'system' -%}
114
+ <|system|>{{ visible_text(m.content) }}
115
+ {%- endif -%}
116
+ {%- endfor -%}
117
+ {%- if add_generation_prompt -%}
118
+ <|assistant|>{{- '<think></think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
119
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,449 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GlmMoeDsaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": [
10
+ 154820,
11
+ 154827,
12
+ 154829
13
+ ],
14
+ "ep_size": 1,
15
+ "first_k_dense_replace": 3,
16
+ "head_dim": 64,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 6144,
19
+ "index_head_dim": 128,
20
+ "index_n_heads": 32,
21
+ "index_share_for_mtp_iteration": true,
22
+ "index_skip_topk_offset": 3,
23
+ "index_topk": 2048,
24
+ "index_topk_freq": 4,
25
+ "index_topk_pattern": null,
26
+ "indexer_rope_interleave": true,
27
+ "indexer_types": [
28
+ "full",
29
+ "full",
30
+ "full",
31
+ "shared",
32
+ "shared",
33
+ "shared",
34
+ "full",
35
+ "shared",
36
+ "shared",
37
+ "shared",
38
+ "full",
39
+ "shared",
40
+ "shared",
41
+ "shared",
42
+ "full",
43
+ "shared",
44
+ "shared",
45
+ "shared",
46
+ "full",
47
+ "shared",
48
+ "shared",
49
+ "shared",
50
+ "full",
51
+ "shared",
52
+ "shared",
53
+ "shared",
54
+ "full",
55
+ "shared",
56
+ "shared",
57
+ "shared",
58
+ "full",
59
+ "shared",
60
+ "shared",
61
+ "shared",
62
+ "full",
63
+ "shared",
64
+ "shared",
65
+ "shared",
66
+ "full",
67
+ "shared",
68
+ "shared",
69
+ "shared",
70
+ "full",
71
+ "shared",
72
+ "shared",
73
+ "shared",
74
+ "full",
75
+ "shared",
76
+ "shared",
77
+ "shared",
78
+ "full",
79
+ "shared",
80
+ "shared",
81
+ "shared",
82
+ "full",
83
+ "shared",
84
+ "shared",
85
+ "shared",
86
+ "full",
87
+ "shared",
88
+ "shared",
89
+ "shared",
90
+ "full",
91
+ "shared",
92
+ "shared",
93
+ "shared",
94
+ "full",
95
+ "shared",
96
+ "shared",
97
+ "shared",
98
+ "full",
99
+ "shared",
100
+ "shared",
101
+ "shared",
102
+ "full",
103
+ "shared",
104
+ "shared",
105
+ "shared"
106
+ ],
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 12288,
109
+ "kv_lora_rank": 512,
110
+ "layer_types": [
111
+ "deepseek_sparse_attention",
112
+ "deepseek_sparse_attention",
113
+ "deepseek_sparse_attention",
114
+ "deepseek_sparse_attention",
115
+ "deepseek_sparse_attention",
116
+ "deepseek_sparse_attention",
117
+ "deepseek_sparse_attention",
118
+ "deepseek_sparse_attention",
119
+ "deepseek_sparse_attention",
120
+ "deepseek_sparse_attention",
121
+ "deepseek_sparse_attention",
122
+ "deepseek_sparse_attention",
123
+ "deepseek_sparse_attention",
124
+ "deepseek_sparse_attention",
125
+ "deepseek_sparse_attention",
126
+ "deepseek_sparse_attention",
127
+ "deepseek_sparse_attention",
128
+ "deepseek_sparse_attention",
129
+ "deepseek_sparse_attention",
130
+ "deepseek_sparse_attention",
131
+ "deepseek_sparse_attention",
132
+ "deepseek_sparse_attention",
133
+ "deepseek_sparse_attention",
134
+ "deepseek_sparse_attention",
135
+ "deepseek_sparse_attention",
136
+ "deepseek_sparse_attention",
137
+ "deepseek_sparse_attention",
138
+ "deepseek_sparse_attention",
139
+ "deepseek_sparse_attention",
140
+ "deepseek_sparse_attention",
141
+ "deepseek_sparse_attention",
142
+ "deepseek_sparse_attention",
143
+ "deepseek_sparse_attention",
144
+ "deepseek_sparse_attention",
145
+ "deepseek_sparse_attention",
146
+ "deepseek_sparse_attention",
147
+ "deepseek_sparse_attention",
148
+ "deepseek_sparse_attention",
149
+ "deepseek_sparse_attention",
150
+ "deepseek_sparse_attention",
151
+ "deepseek_sparse_attention",
152
+ "deepseek_sparse_attention",
153
+ "deepseek_sparse_attention",
154
+ "deepseek_sparse_attention",
155
+ "deepseek_sparse_attention",
156
+ "deepseek_sparse_attention",
157
+ "deepseek_sparse_attention",
158
+ "deepseek_sparse_attention",
159
+ "deepseek_sparse_attention",
160
+ "deepseek_sparse_attention",
161
+ "deepseek_sparse_attention",
162
+ "deepseek_sparse_attention",
163
+ "deepseek_sparse_attention",
164
+ "deepseek_sparse_attention",
165
+ "deepseek_sparse_attention",
166
+ "deepseek_sparse_attention",
167
+ "deepseek_sparse_attention",
168
+ "deepseek_sparse_attention",
169
+ "deepseek_sparse_attention",
170
+ "deepseek_sparse_attention",
171
+ "deepseek_sparse_attention",
172
+ "deepseek_sparse_attention",
173
+ "deepseek_sparse_attention",
174
+ "deepseek_sparse_attention",
175
+ "deepseek_sparse_attention",
176
+ "deepseek_sparse_attention",
177
+ "deepseek_sparse_attention",
178
+ "deepseek_sparse_attention",
179
+ "deepseek_sparse_attention",
180
+ "deepseek_sparse_attention",
181
+ "deepseek_sparse_attention",
182
+ "deepseek_sparse_attention",
183
+ "deepseek_sparse_attention",
184
+ "deepseek_sparse_attention",
185
+ "deepseek_sparse_attention",
186
+ "deepseek_sparse_attention",
187
+ "deepseek_sparse_attention",
188
+ "deepseek_sparse_attention"
189
+ ],
190
+ "max_position_embeddings": 1048576,
191
+ "mlp_bias": false,
192
+ "mlp_layer_types": [
193
+ "dense",
194
+ "dense",
195
+ "dense",
196
+ "sparse",
197
+ "sparse",
198
+ "sparse",
199
+ "sparse",
200
+ "sparse",
201
+ "sparse",
202
+ "sparse",
203
+ "sparse",
204
+ "sparse",
205
+ "sparse",
206
+ "sparse",
207
+ "sparse",
208
+ "sparse",
209
+ "sparse",
210
+ "sparse",
211
+ "sparse",
212
+ "sparse",
213
+ "sparse",
214
+ "sparse",
215
+ "sparse",
216
+ "sparse",
217
+ "sparse",
218
+ "sparse",
219
+ "sparse",
220
+ "sparse",
221
+ "sparse",
222
+ "sparse",
223
+ "sparse",
224
+ "sparse",
225
+ "sparse",
226
+ "sparse",
227
+ "sparse",
228
+ "sparse",
229
+ "sparse",
230
+ "sparse",
231
+ "sparse",
232
+ "sparse",
233
+ "sparse",
234
+ "sparse",
235
+ "sparse",
236
+ "sparse",
237
+ "sparse",
238
+ "sparse",
239
+ "sparse",
240
+ "sparse",
241
+ "sparse",
242
+ "sparse",
243
+ "sparse",
244
+ "sparse",
245
+ "sparse",
246
+ "sparse",
247
+ "sparse",
248
+ "sparse",
249
+ "sparse",
250
+ "sparse",
251
+ "sparse",
252
+ "sparse",
253
+ "sparse",
254
+ "sparse",
255
+ "sparse",
256
+ "sparse",
257
+ "sparse",
258
+ "sparse",
259
+ "sparse",
260
+ "sparse",
261
+ "sparse",
262
+ "sparse",
263
+ "sparse",
264
+ "sparse",
265
+ "sparse",
266
+ "sparse",
267
+ "sparse",
268
+ "sparse",
269
+ "sparse",
270
+ "sparse"
271
+ ],
272
+ "model_type": "glm_moe_dsa",
273
+ "moe_intermediate_size": 2048,
274
+ "moe_layer_freq": 1,
275
+ "n_group": 1,
276
+ "n_routed_experts": 168,
277
+ "n_shared_experts": 1,
278
+ "norm_topk_prob": true,
279
+ "num_attention_heads": 64,
280
+ "num_experts": 256,
281
+ "num_experts_per_tok": 8,
282
+ "num_hidden_layers": 78,
283
+ "num_key_value_heads": 64,
284
+ "num_nextn_predict_layers": 1,
285
+ "pad_token_id": 154820,
286
+ "pretraining_tp": 1,
287
+ "q_lora_rank": 2048,
288
+ "qk_head_dim": 256,
289
+ "qk_nope_head_dim": 192,
290
+ "qk_rope_head_dim": 64,
291
+ "quantization_config": {
292
+ "autoround_version": "0.13.1",
293
+ "batch_size": 4,
294
+ "bits": 4,
295
+ "block_name_to_quantize": "model.layers",
296
+ "data_type": "int",
297
+ "extra_config": {
298
+ ".*layers\\.[0-2]\\.mlp.*": {
299
+ "bits": 16,
300
+ "data_type": "float"
301
+ },
302
+ ".*weights_proj.*": {
303
+ "bits": 16,
304
+ "data_type": "float"
305
+ },
306
+ "model.layers.0.mlp.down_proj": {
307
+ "bits": 16,
308
+ "data_type": "float"
309
+ },
310
+ "model.layers.0.mlp.gate_proj": {
311
+ "bits": 16,
312
+ "data_type": "float"
313
+ },
314
+ "model.layers.0.mlp.up_proj": {
315
+ "bits": 16,
316
+ "data_type": "float"
317
+ },
318
+ "model.layers.0.self_attn.indexer.weights_proj": {
319
+ "bits": 16,
320
+ "data_type": "float"
321
+ },
322
+ "model.layers.1.mlp.down_proj": {
323
+ "bits": 16,
324
+ "data_type": "float"
325
+ },
326
+ "model.layers.1.mlp.gate_proj": {
327
+ "bits": 16,
328
+ "data_type": "float"
329
+ },
330
+ "model.layers.1.mlp.up_proj": {
331
+ "bits": 16,
332
+ "data_type": "float"
333
+ },
334
+ "model.layers.1.self_attn.indexer.weights_proj": {
335
+ "bits": 16,
336
+ "data_type": "float"
337
+ },
338
+ "model.layers.10.self_attn.indexer.weights_proj": {
339
+ "bits": 16,
340
+ "data_type": "float"
341
+ },
342
+ "model.layers.14.self_attn.indexer.weights_proj": {
343
+ "bits": 16,
344
+ "data_type": "float"
345
+ },
346
+ "model.layers.18.self_attn.indexer.weights_proj": {
347
+ "bits": 16,
348
+ "data_type": "float"
349
+ },
350
+ "model.layers.2.mlp.down_proj": {
351
+ "bits": 16,
352
+ "data_type": "float"
353
+ },
354
+ "model.layers.2.mlp.gate_proj": {
355
+ "bits": 16,
356
+ "data_type": "float"
357
+ },
358
+ "model.layers.2.mlp.up_proj": {
359
+ "bits": 16,
360
+ "data_type": "float"
361
+ },
362
+ "model.layers.2.self_attn.indexer.weights_proj": {
363
+ "bits": 16,
364
+ "data_type": "float"
365
+ },
366
+ "model.layers.22.self_attn.indexer.weights_proj": {
367
+ "bits": 16,
368
+ "data_type": "float"
369
+ },
370
+ "model.layers.26.self_attn.indexer.weights_proj": {
371
+ "bits": 16,
372
+ "data_type": "float"
373
+ },
374
+ "model.layers.30.self_attn.indexer.weights_proj": {
375
+ "bits": 16,
376
+ "data_type": "float"
377
+ },
378
+ "model.layers.34.self_attn.indexer.weights_proj": {
379
+ "bits": 16,
380
+ "data_type": "float"
381
+ },
382
+ "model.layers.38.self_attn.indexer.weights_proj": {
383
+ "bits": 16,
384
+ "data_type": "float"
385
+ },
386
+ "model.layers.42.self_attn.indexer.weights_proj": {
387
+ "bits": 16,
388
+ "data_type": "float"
389
+ },
390
+ "model.layers.46.self_attn.indexer.weights_proj": {
391
+ "bits": 16,
392
+ "data_type": "float"
393
+ },
394
+ "model.layers.50.self_attn.indexer.weights_proj": {
395
+ "bits": 16,
396
+ "data_type": "float"
397
+ },
398
+ "model.layers.54.self_attn.indexer.weights_proj": {
399
+ "bits": 16,
400
+ "data_type": "float"
401
+ },
402
+ "model.layers.58.self_attn.indexer.weights_proj": {
403
+ "bits": 16,
404
+ "data_type": "float"
405
+ },
406
+ "model.layers.6.self_attn.indexer.weights_proj": {
407
+ "bits": 16,
408
+ "data_type": "float"
409
+ },
410
+ "model.layers.62.self_attn.indexer.weights_proj": {
411
+ "bits": 16,
412
+ "data_type": "float"
413
+ },
414
+ "model.layers.66.self_attn.indexer.weights_proj": {
415
+ "bits": 16,
416
+ "data_type": "float"
417
+ },
418
+ "model.layers.70.self_attn.indexer.weights_proj": {
419
+ "bits": 16,
420
+ "data_type": "float"
421
+ },
422
+ "model.layers.74.self_attn.indexer.weights_proj": {
423
+ "bits": 16,
424
+ "data_type": "float"
425
+ }
426
+ },
427
+ "group_size": 128,
428
+ "low_gpu_mem_usage": true,
429
+ "nsamples": 512,
430
+ "packing_format": "auto_round:auto_gptq",
431
+ "quant_method": "auto-round",
432
+ "sym": true
433
+ },
434
+ "rms_norm_eps": 1e-05,
435
+ "rope_interleave": true,
436
+ "rope_parameters": {
437
+ "rope_theta": 8000000,
438
+ "rope_type": "default"
439
+ },
440
+ "routed_scaling_factor": 2.5,
441
+ "scoring_func": "sigmoid",
442
+ "tie_word_embeddings": false,
443
+ "topk_group": 1,
444
+ "topk_method": "noaux_tc",
445
+ "transformers_version": "5.12.1",
446
+ "use_cache": true,
447
+ "v_head_dim": 256,
448
+ "vocab_size": 154880
449
+ }
model-00001-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5904d65fb344992656b602eda5fb3272013e7e8c079b88c56a8b277c67872d4
3
+ size 5368286104
model-00002-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c753cd73aa7eda87191018732f131d8c0cfdc4266acc1ed3eb224dff1b6ea2d
3
+ size 5363657920
model-00003-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93f65fd745250e2399bf87ba43f3ed05b3cc30ea7db4a0bc78f6ccaaf30d6f5
3
+ size 5365123720
model-00004-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ab319c9a68f3da4822aabb835bcf30819faed8c1bc39e11814b36e0aa83a618
3
+ size 5363658160
model-00005-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6b332be8627c981fb4d3bd7baecd64d729d3c5bb685d7cf1ce8badbe124c25
3
+ size 5365124096
model-00006-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28470e0a3ee03b162f9b3929bc4cc65a5c07492dd8dadd17d8790014b376addf
3
+ size 5363660840
model-00007-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b75402f2b95b75dbf2aa5b2e4aec187bdede08dcee6e8368e9ec3bbfdcb026
3
+ size 5366501720
model-00008-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd0d3a873281f9e382898599e80a84658b3b236a73dfe43a6df841f7c462c6a
3
+ size 5365126264
model-00009-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def468e7a4660d94f9f808918c6805e537cdca53a678920565eebcd8915650eb
3
+ size 5363660416
model-00010-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36237cdc22dd4aade4ef618cfa5a755dc6779ef269a0b66dc9b323150f90d087
3
+ size 5365126104
model-00011-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7001cf5fdcd522d783aa26ab6bc0bc8ad8b2284edc299a8ec851b777420bd401
3
+ size 5363660656
model-00012-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4e94b9b8460c067fbba2c10dc6a9f08bb19b10e3ecdb0e4ab69a39f0707a80
3
+ size 5366501912
model-00013-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3839ac40254b43d52d26d046db55d9746baedc839690976639ed0fc01e332825
3
+ size 5358591360
model-00014-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65bd541f086e77b4ef3f06051172a01efd52745e6b7412fb462747fff80a75fd
3
+ size 5363657568
model-00015-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eedc17b816ce04efec40fc2879f9e74c95ff81dabb229e7e29d5331f10f900a
3
+ size 5365126264
model-00016-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59410b26b95f55b7c4a00ffa23cfcea7524063d3f4ab8e8b2f5b5babdf43e933
3
+ size 5363660464
model-00017-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8f36faf15d9f56179642fa2f465d7623e632423888f7115da9f59fc18bd0d7
3
+ size 5366502096
model-00018-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0dd2b8d8f37487654ede600b86816341a6044ca22774646e77bd793d5a06b80
3
+ size 5368822240
model-00019-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8858c2c4c200cf94ad3dc5caf3d0ea15ec60f1e3d1eb5da1182c037797795868
3
+ size 5366501856
model-00020-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874f3bdcaa6c0ce5cdf25637794cc0fcaa4b64d028d2f9a8b8812cbc38314270
3
+ size 5365126328
model-00021-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94155143f17369414bc51ae2465387f66d18c92ec4756b4820b2541f02afd7e3
3
+ size 5363660224
model-00022-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd37f7bad35c9ff5e67438ae4d04247865ecafe673d7d5b8a4803b54e78ac25
3
+ size 5366502280
model-00023-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e865442f2000f0355e9ecd79e2ad6a32b58a04e809cb0fb166841fd382ac019
3
+ size 5368822056
model-00024-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0e3358e4e85bca53fee33307dcbefa3431c08ebac41c2cdd457070c81ce902
3
+ size 5366502048
model-00025-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f239c8e133bbb7edfaa9e1371850dc4656f452e9cbe394546c40ea3cd776c10c
3
+ size 5363660760
model-00026-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3362616fd4cf0d60857992e0de3f466a6a2ac3f77c8e4526087a31eb4f8e88
3
+ size 5365125752
model-00027-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e441f8cd63a66d5fc8480b6f995d9d3a36c2a05202ede3bce1d797dbc91ebf9
3
+ size 5366502320
model-00028-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1f8acaf385d98669064411908b8fd77e1c7f4e41dd4bb9432b031ee903d1e5
3
+ size 5368821872
model-00029-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f9903e12daf98957260e1bb4fcdf6bc49530b224231fb53266db877c6e3c99
3
+ size 5366502224
model-00030-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ec7c8403ed2b87b440f3c4217514f467d29a237bfecf072f602f04a47af771
3
+ size 5363660576
model-00031-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a3627ed197c2d8fecc2c7ccea89aa70e0e8cbc17d348581848afea63c5ce05
3
+ size 5365125936
model-00032-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9767093dcfce75ae070e9c53fb86e26c26081572b545592d83ddb513df8d120a
3
+ size 5363660816
model-00033-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40ce53df9f62a5b10ad88eea88e9ca0a1065219122c46bfd4766f26b056b94b
3
+ size 5365125696
model-00034-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:113cf9cb316f5f19a1547b4ea432f2a565970594daa91f01e8743405a2db4bb4
3
+ size 5366502320
model-00035-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8186dad1ce71be457babe70d2fe5e9b272502524ba09052c212e43c05fc67f32
3
+ size 5363660392
model-00036-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173ca0ddaca515146fda7e731ff3c4c801c6b04ff6dfedd4428cdce2eec1cbac
3
+ size 5365126120
model-00037-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71276d6b90ba26bb28b7aa5dc25a471a209e9e2e4cd80a4069ef60417257273
3
+ size 5363660632
model-00038-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413cab7177c6a3b0c4631a35982d2e36a844559395d9b9aa1eb5cd9397c38828
3
+ size 5365125888
model-00039-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09794ac38b513bd48b4e853c307245f8de4a5aa0bfee6784738e58d6df302d8
3
+ size 5365726152
model-00040-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55128ff66a498b94f5850e4a0b112cfc9ac60c976e3053e4f66e1ba268a66393
3
+ size 5364436416
model-00041-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfddc7d46c3ca9f5f67eda220cf0a05bd9d9d0349bb1dd77c6e20ae247a5ac6
3
+ size 5365126264
model-00042-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96616a1badcefdede0289e27ca28ca6aa81e831cf35f980bdb0a165d7deac1be
3
+ size 5363660440
model-00043-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26a2907ef1b4e604b9cbccececf3ea5ef8fb93058e8b65dbf0937576351605d
3
+ size 5365126072
model-00044-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbd9479642831e4e35ee8a92dbbeb4de68b9a7fde31e182a6afa70d1a55c5f9
3
+ size 5363660680
model-00045-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07eeec9eaa95d00289a62f1b20e3f5108f5e97fcc99ab6de6130c50e6f3f4fe0
3
+ size 5366501880
model-00046-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3fb7eac31d5c87d3818138a78217d60bd3043a446788681c950b96fa9b4058
3
+ size 5365126352
model-00047-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a87ff34f73f943ff9e579bb3068b3cd28fbc9ed03bf2143e5ff6e8f393fb42
3
+ size 5363660176