yiqichen01 commited on
Commit
79e5698
·
verified ·
1 Parent(s): c1ce445

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. chat_template.jinja +309 -0
  2. config.json +651 -0
  3. generation_config.json +10 -0
  4. model-00001-of-00130.safetensors +3 -0
  5. model-00002-of-00130.safetensors +3 -0
  6. model-00003-of-00130.safetensors +3 -0
  7. model-00004-of-00130.safetensors +3 -0
  8. model-00005-of-00130.safetensors +3 -0
  9. model-00006-of-00130.safetensors +3 -0
  10. model-00007-of-00130.safetensors +3 -0
  11. model-00008-of-00130.safetensors +3 -0
  12. model-00009-of-00130.safetensors +3 -0
  13. model-00010-of-00130.safetensors +3 -0
  14. model-00011-of-00130.safetensors +3 -0
  15. model-00012-of-00130.safetensors +3 -0
  16. model-00013-of-00130.safetensors +3 -0
  17. model-00014-of-00130.safetensors +3 -0
  18. model-00015-of-00130.safetensors +3 -0
  19. model-00016-of-00130.safetensors +3 -0
  20. model-00017-of-00130.safetensors +3 -0
  21. model-00018-of-00130.safetensors +3 -0
  22. model-00019-of-00130.safetensors +3 -0
  23. model-00020-of-00130.safetensors +3 -0
  24. model-00021-of-00130.safetensors +3 -0
  25. model-00022-of-00130.safetensors +3 -0
  26. model-00023-of-00130.safetensors +3 -0
  27. model-00024-of-00130.safetensors +3 -0
  28. model-00025-of-00130.safetensors +3 -0
  29. model-00026-of-00130.safetensors +3 -0
  30. model-00027-of-00130.safetensors +3 -0
  31. model-00028-of-00130.safetensors +3 -0
  32. model-00029-of-00130.safetensors +3 -0
  33. model-00030-of-00130.safetensors +3 -0
  34. model-00031-of-00130.safetensors +3 -0
  35. model-00032-of-00130.safetensors +3 -0
  36. model-00033-of-00130.safetensors +3 -0
  37. model-00034-of-00130.safetensors +3 -0
  38. model-00035-of-00130.safetensors +3 -0
  39. model-00036-of-00130.safetensors +3 -0
  40. model-00037-of-00130.safetensors +3 -0
  41. model-00038-of-00130.safetensors +3 -0
  42. model-00039-of-00130.safetensors +3 -0
  43. model-00040-of-00130.safetensors +3 -0
  44. model-00041-of-00130.safetensors +3 -0
  45. model-00042-of-00130.safetensors +3 -0
  46. model-00043-of-00130.safetensors +3 -0
  47. model-00044-of-00130.safetensors +3 -0
  48. model-00045-of-00130.safetensors +3 -0
  49. model-00046-of-00130.safetensors +3 -0
  50. model-00047-of-00130.safetensors +3 -0
chat_template.jinja ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {#- ----------‑‑‑ special token variables ‑‑‑---------- -#}
2
+ {%- set HYTK = ':opensource' %}
3
+ {%- set hy_start_token = '<|hy_start{}|>'.format(HYTK) %}
4
+ {%- set hy_middle_token = '<|hy_middle{}|>'.format(HYTK) %}
5
+ {%- set hy_end_token = '<|hy_end{}|>'.format(HYTK) %}
6
+ {%- set think_begin_token = '<think{}>'.format(HYTK) %}
7
+ {%- set think_end_token = '</think{}>'.format(HYTK) %}
8
+ {%- set toolcalls_begin_token = '<tool_calls{}>'.format(HYTK) %}
9
+ {%- set toolcalls_end_token = '</tool_calls{}>'.format(HYTK) %}
10
+ {%- set toolcall_begin_token = '<tool_call{}>'.format(HYTK) %}
11
+ {%- set toolcall_end_token = '</tool_call{}>'.format(HYTK) %}
12
+ {%- set argkey_begin_token = '<arg_key{}>'.format(HYTK) %}
13
+ {%- set argkey_end_token = '</arg_key{}>'.format(HYTK) %}
14
+ {%- set argvalue_begin_token = '<arg_value{}>'.format(HYTK) %}
15
+ {%- set argvalue_end_token = '</arg_value{}>'.format(HYTK) %}
16
+ {%- set toolresponse_begin_token = '<tool_response{}>'.format(HYTK) %}
17
+ {%- set toolresponse_end_token = '</tool_response{}>'.format(HYTK) %}
18
+ {%- set reasoning_mode_token = '<|reasoning_mode{}|>'.format(HYTK) %}
19
+
20
+ {#- ----------‑‑‑ hyperparameters variables ‑‑‑---------- -#}
21
+ {%- if not add_generation_prompt is defined %}
22
+ {%- set add_generation_prompt = false %}
23
+ {%- endif %}
24
+ {%- if not preserved_thinking is defined %}
25
+ {%- if not tools %}
26
+ {%- set preserved_thinking = false %}
27
+ {%- else %}
28
+ {%- set preserved_thinking = true %}
29
+ {%- endif %}
30
+ {%- endif %}
31
+
32
+ {%- if not reasoning_effort is defined %}
33
+ {%- set reasoning_effort = 'high' %}
34
+ {%- elif reasoning_effort not in ['high', 'no_think'] %}
35
+ {%- if reasoning_effort is none %}
36
+ {{- raise_exception('reasoning_effort error : None, should be no_think/high') }}
37
+ {%- else %}
38
+ {{- raise_exception('reasoning_effort error : ' + reasoning_effort + ', should be no_think/high') }}
39
+ {%- endif %}
40
+ {%- endif %}
41
+
42
+ {%- if fallback_strategy is defined and fallback_strategy == 'reasoning_toolcall_retry' %}
43
+ {%- set reasoning_effort = 'high' %}
44
+ {%- set add_generation_prompt = false %}
45
+ {%- endif %}
46
+ {%- if not raw_last_assistant is defined %}
47
+ {%- set raw_last_assistant = false %}
48
+ {%- endif %}
49
+
50
+ {%- macro tool_to_json(tool) -%}
51
+ {%- set ns_tool = namespace(first=true) -%}
52
+ {{- '{' -}}
53
+ {%- for k, v in tool.items() -%}
54
+ {%- if k != 'defer_loading' and k != 'strict' -%}
55
+ {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
56
+ {%- set ns_tool.first = false -%}
57
+ {{- '"' ~ k ~ '": ' ~ (v | tojson(ensure_ascii=False)) -}}
58
+ {%- endif -%}
59
+ {%- endfor -%}
60
+ {{- '}' -}}
61
+ {%- endmacro -%}
62
+
63
+ {%- macro render_content(content) -%}
64
+ {%- if content is string -%}
65
+ {{- content -}}
66
+ {%- elif content is iterable and content is not mapping -%}
67
+ {%- for item in content -%}
68
+ {%- if item is mapping and item.type == 'text' -%}
69
+ {{- item.text -}}
70
+ {%- elif item is string -%}
71
+ {{- item -}}
72
+ {%- else -%}
73
+ {{- item | string -}}
74
+ {%- endif -%}
75
+ {%- endfor -%}
76
+ {%- elif content is none -%}
77
+ {{- '' -}}
78
+ {%- else -%}
79
+ {{- content | string -}}
80
+ {%- endif -%}
81
+ {%- endmacro -%}
82
+
83
+ {%- macro render_tools_prompt() -%}
84
+ {{- '# Tools\n\nYou may call one or more functions to assist with the user query.' -}}
85
+ {{- '\n\nYou are provided with function signatures within <tools></tools> XML tags:' -}}
86
+ {{- '\n<tools>\n' -}}
87
+ {%- set tool_ns = namespace(first=true) -%}
88
+ {%- for tool in tools -%}
89
+ {%- set t = tool['function'] if tool is mapping and 'function' in tool else tool -%}
90
+ {%- if t.defer_loading is not defined or not t.defer_loading -%}
91
+ {%- if not tool_ns.first -%}{{- '\n' -}}{%- endif -%}
92
+ {%- set tool_ns.first = false -%}
93
+ {{- tool_to_json(t) -}}
94
+ {%- endif -%}
95
+ {%- endfor -%}
96
+ {{- '\n</tools>\n\n' -}}
97
+ {{- 'For function call returns, you should first print ' ~ toolcalls_begin_token -}}
98
+ {{- '\nFor each function call, you should return object like:\n' -}}
99
+ {{- toolcall_begin_token ~ '{function-name}' -}}
100
+ {{- argkey_begin_token ~ '{arg-key-1}' ~ argkey_end_token -}}
101
+ {{- argvalue_begin_token ~ '{arg-value-1}' ~ argvalue_end_token -}}
102
+ {{- argkey_begin_token ~ '{arg-key-2}' ~ argkey_end_token -}}
103
+ {{- argvalue_begin_token ~ '{arg-value-2}' ~ argvalue_end_token -}}
104
+ {{- '...' -}}
105
+ {{- toolcall_end_token -}}
106
+ {{- '\nAt the end of function call returns, you should print ' ~ toolcalls_end_token -}}
107
+ {%- endmacro -%}
108
+
109
+ {%- macro render_tool_response(message) -%}
110
+ {%- set content = message['content'] -%}
111
+ {%- if content is string -%}
112
+ {{- toolresponse_begin_token ~ content ~ toolresponse_end_token -}}
113
+ {%- elif content is iterable and content is not mapping and content and content[0] is mapping and content[0].type == 'tool_reference' -%}
114
+ {{- toolresponse_begin_token -}}
115
+ {{- '<tools>\n' -}}
116
+ {%- for tr in content -%}
117
+ {%- for tool in tools -%}
118
+ {%- set t = tool['function'] if tool is mapping and 'function' in tool else tool -%}
119
+ {%- if t.name == tr.name -%}
120
+ {{- tool_to_json(t) ~ '\n' -}}
121
+ {%- endif -%}
122
+ {%- endfor -%}
123
+ {%- endfor -%}
124
+ {{- '</tools>' -}}
125
+ {{- toolresponse_end_token -}}
126
+ {%- elif content is iterable and content is not mapping and content and content[0] is mapping and content[0].output is defined -%}
127
+ {%- for tr in content -%}
128
+ {{- toolresponse_begin_token ~ tr.output ~ toolresponse_end_token -}}
129
+ {%- endfor -%}
130
+ {%- else -%}
131
+ {{- toolresponse_begin_token ~ render_content(content) ~ toolresponse_end_token -}}
132
+ {%- endif -%}
133
+ {%- endmacro -%}
134
+
135
+ {#- consecutive tool messages are clustered into a single tool message whose content is the list of the original tool messages; the result is written to merged_ns.messages (a macro cannot return a list) -#}
136
+ {%- set merged_ns = namespace(messages=[]) %}
137
+ {%- macro merge_tool_responses(messages) -%}
138
+ {%- set merge_ns = namespace(result=[], cluster=[]) -%}
139
+ {%- for message in messages -%}
140
+ {%- if message['role'] == 'tool' -%}
141
+ {%- set merge_ns.cluster = merge_ns.cluster + [message] -%}
142
+ {%- else -%}
143
+ {%- if merge_ns.cluster -%}
144
+ {%- set merge_ns.result = merge_ns.result + [{'role': 'tool', 'content': merge_ns.cluster}] -%}
145
+ {%- set merge_ns.cluster = [] -%}
146
+ {%- endif -%}
147
+ {%- set merge_ns.result = merge_ns.result + [message] -%}
148
+ {%- endif -%}
149
+ {%- endfor -%}
150
+ {%- if merge_ns.cluster -%}
151
+ {%- set merge_ns.result = merge_ns.result + [{'role': 'tool', 'content': merge_ns.cluster}] -%}
152
+ {%- endif -%}
153
+ {%- set merged_ns.messages = merge_ns.result -%}
154
+ {%- endmacro -%}
155
+
156
+ {#- render one tool cluster, reordered to follow the tool_call order of the preceding assistant turn; any missing / ambiguous id falls back to the original tool message order for the whole cluster -#}
157
+ {%- macro render_tool_responses(tool_messages, tool_call_ids) -%}
158
+ {%- set order_ns = namespace(ordered=[], matched=true) -%}
159
+ {%- if tool_call_ids and tool_call_ids | length == tool_messages | length -%}
160
+ {%- for tool_call_id in tool_call_ids -%}
161
+ {%- set hit_ns = namespace(count=0, message=none) -%}
162
+ {%- for tool_message in tool_messages -%}
163
+ {%- set message_id = tool_message['tool_call_id'] if tool_message['tool_call_id'] is defined else tool_message['id'] -%}
164
+ {%- if message_id is defined and message_id == tool_call_id -%}
165
+ {%- set hit_ns.count = hit_ns.count + 1 -%}
166
+ {%- set hit_ns.message = tool_message -%}
167
+ {%- endif -%}
168
+ {%- endfor -%}
169
+ {%- if hit_ns.count == 1 -%}
170
+ {%- set order_ns.ordered = order_ns.ordered + [hit_ns.message] -%}
171
+ {%- else -%}
172
+ {%- set order_ns.matched = false -%}
173
+ {%- endif -%}
174
+ {%- endfor -%}
175
+ {%- else -%}
176
+ {%- set order_ns.matched = false -%}
177
+ {%- endif -%}
178
+ {%- for tool_message in (order_ns.ordered if order_ns.matched else tool_messages) -%}
179
+ {{- render_tool_response(tool_message) -}}
180
+ {%- endfor -%}
181
+ {%- endmacro -%}
182
+
183
+ {%- set _ = merge_tool_responses(messages) %}
184
+ {%- set normed_messages = merged_ns.messages %}
185
+
186
+ {%- set ns = namespace(last_user_index=-1, has_leading_system=false) %}
187
+ {%- if normed_messages and normed_messages[0].role == 'system' %}
188
+ {%- set ns.has_leading_system = true %}
189
+ {%- endif %}
190
+ {%- for message in normed_messages %}
191
+ {%- if message['role'] == 'user' %}
192
+ {%- set ns.last_user_index = loop.index0 %}
193
+ {%- endif %}
194
+ {%- endfor %}
195
+
196
+ {#- no leading system: synthesize one for tools and/or reasoning_mode -#}
197
+ {%- if not ns.has_leading_system %}
198
+ {{- hy_start_token ~ 'system' ~ hy_middle_token -}}
199
+ {%- if tools %}
200
+ {{- render_tools_prompt() -}}
201
+ {%- endif %}
202
+ {{- reasoning_mode_token ~ 'reasoning_effort:' ~ reasoning_effort -}}
203
+ {{- hy_end_token -}}
204
+ {%- endif %}
205
+
206
+ {%- set last_ns = namespace(last_is_assistant=false) %}
207
+ {%- set prev_ns = namespace(tool_call_ids=[]) %}
208
+ {%- for message in normed_messages %}
209
+ {%- if message['role'] == 'system' %}
210
+ {{- hy_start_token ~ 'system' ~ hy_middle_token -}}
211
+ {#- tools / reasoning_mode only attach to the leading system (messages[0]) -#}
212
+ {%- if loop.first %}
213
+ {%- if tools %}
214
+ {{- render_tools_prompt() -}}
215
+ {%- endif %}
216
+ {%- set content = render_content(message['content']) -%}
217
+ {%- if tools and content -%}
218
+ {{- '\n\n' -}}
219
+ {%- endif -%}
220
+ {{- content -}}
221
+ {{- reasoning_mode_token ~ 'reasoning_effort:' ~ reasoning_effort -}}
222
+ {%- else %}
223
+ {{- render_content(message['content']) -}}
224
+ {%- endif %}
225
+ {{- hy_end_token -}}
226
+ {%- elif message['role'] == 'user' %}
227
+ {{- hy_start_token ~ 'user' ~ hy_middle_token -}}
228
+ {{- render_content(message['content']) -}}
229
+ {{- hy_end_token -}}
230
+ {%- elif message['role'] == 'assistant' %}
231
+ {%- set content_body = render_content(message['content']) -%}
232
+ {#- 'reasoning' takes precedence, fall back to 'reasoning_content' when it is empty -#}
233
+ {%- set reasoning_text = '' %}
234
+ {%- if message['reasoning'] is defined and message['reasoning'] is string and message['reasoning'] %}
235
+ {%- set reasoning_text = message['reasoning'] %}
236
+ {%- elif message['reasoning_content'] is defined and message['reasoning_content'] is string and message['reasoning_content'] %}
237
+ {%- set reasoning_text = message['reasoning_content'] %}
238
+ {%- endif %}
239
+ {#- no_think overrides preserved_thinking: history is always emitted with empty think tags -#}
240
+ {%- if reasoning_effort != 'no_think' and (preserved_thinking or loop.index0 > ns.last_user_index) and reasoning_text %}
241
+ {%- set content = think_begin_token ~ reasoning_text ~ think_end_token ~ content_body %}
242
+ {%- else %}
243
+ {%- set content = think_begin_token ~ think_end_token ~ content_body %}
244
+ {%- endif %}
245
+ {{- hy_start_token ~ 'assistant' ~ hy_middle_token -}}
246
+ {%- if message['tool_calls'] is defined and message['tool_calls'] %}
247
+ {#- remember the tool_call ids of this turn to order the following tool responses; an incomplete id set means "do not reorder" -#}
248
+ {%- set ids_ns = namespace(ids=[], complete=true) %}
249
+ {%- for tool in message['tool_calls'] %}
250
+ {%- set tool_call_id = tool['id'] if tool['id'] is defined and tool['id'] else tool['tool_call_id'] %}
251
+ {%- if tool_call_id is defined and tool_call_id %}
252
+ {%- set ids_ns.ids = ids_ns.ids + [tool_call_id] %}
253
+ {%- else %}
254
+ {%- set ids_ns.complete = false %}
255
+ {%- endif %}
256
+ {%- endfor %}
257
+ {%- set prev_ns.tool_call_ids = ids_ns.ids if ids_ns.complete else [] %}
258
+ {{- content -}}
259
+ {{- toolcalls_begin_token -}}
260
+ {%- for tool in message['tool_calls'] -%}
261
+ {%- set func = tool['function'] if tool is mapping and 'function' in tool else tool -%}
262
+ {%- set arguments = func['arguments'] -%}
263
+ {{- toolcall_begin_token ~ func['name'] -}}
264
+ {%- for key, value in arguments.items() -%}
265
+ {{- argkey_begin_token ~ key ~ argkey_end_token -}}
266
+ {%- if value is not string -%}
267
+ {%- set value = value | tojson(ensure_ascii=False) -%}
268
+ {%- endif -%}
269
+ {{- argvalue_begin_token ~ value ~ argvalue_end_token -}}
270
+ {%- endfor -%}
271
+ {{- toolcall_end_token -}}
272
+ {%- endfor -%}
273
+ {{- toolcalls_end_token -}}
274
+ {%- else %}
275
+ {%- if loop.last and raw_last_assistant %}
276
+ {{- content_body -}}
277
+ {%- else %}
278
+ {{- content -}}
279
+ {%- endif %}
280
+ {%- endif %}
281
+ {#- continuation / prefill: last assistant is still open, do not close with hy_end -#}
282
+ {%- if not (loop.last and raw_last_assistant) and not (loop.last and fallback_strategy is defined and fallback_strategy == 'reasoning_toolcall_retry') %}
283
+ {{- hy_end_token -}}
284
+ {%- endif %}
285
+ {%- elif message['role'] == 'tool' %}
286
+ {{- hy_start_token ~ 'tool' ~ hy_middle_token -}}
287
+ {{- render_tool_responses(message['content'], prev_ns.tool_call_ids) -}}
288
+ {{- hy_end_token -}}
289
+ {%- else %}
290
+ {{- hy_start_token ~ message['role'] ~ hy_middle_token -}}
291
+ {{- render_content(message['content']) -}}
292
+ {{- hy_end_token -}}
293
+ {%- endif %}
294
+ {%- if message['role'] != 'assistant' or not (message['tool_calls'] is defined and message['tool_calls']) %}
295
+ {%- set prev_ns.tool_call_ids = [] %}
296
+ {%- endif %}
297
+ {%- if loop.last and message['role'] == 'assistant' %}
298
+ {%- set last_ns.last_is_assistant = true %}
299
+ {%- endif %}
300
+ {%- endfor %}
301
+ {%- if add_generation_prompt %}
302
+ {%- if not last_ns.last_is_assistant %}
303
+ {%- if reasoning_effort == 'no_think' %}
304
+ {{- hy_start_token ~ 'assistant' ~ hy_middle_token ~ think_begin_token ~ think_end_token -}}
305
+ {%- else %}
306
+ {{- hy_start_token ~ 'assistant' ~ hy_middle_token ~ think_begin_token -}}
307
+ {%- endif %}
308
+ {%- endif %}
309
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,651 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HYV4ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bitwise_backward_align": false,
8
+ "bos_token_id": 120000,
9
+ "dtype": "bfloat16",
10
+ "enable_ihc": true,
11
+ "enable_lm_head_fp32": true,
12
+ "eos_token_id": 120025,
13
+ "gated_mla": true,
14
+ "gating_type": "elementwise",
15
+ "hc_eps": 1e-06,
16
+ "hc_magnitude": 2.0,
17
+ "hc_mult": 4,
18
+ "head_dim": 64,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 6144,
21
+ "index_head_dim": 128,
22
+ "index_n_heads": 32,
23
+ "index_topk": 2048,
24
+ "indexer_types": [
25
+ "full",
26
+ "full",
27
+ "shared",
28
+ "shared",
29
+ "shared",
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
+ ],
104
+ "initializer_range": 0.006,
105
+ "intermediate_size": 18432,
106
+ "kv_lora_rank": 512,
107
+ "layer_types": [
108
+ "deepseek_sparse_attention",
109
+ "deepseek_sparse_attention",
110
+ "deepseek_sparse_attention",
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
+ ],
187
+ "learnable_sink": true,
188
+ "learnable_sink_init": 0.0,
189
+ "max_position_embeddings": 1048576,
190
+ "mlp_layer_types": [
191
+ "dense",
192
+ "sparse",
193
+ "sparse",
194
+ "sparse",
195
+ "sparse",
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
+ ],
270
+ "model_type": "hy_v4",
271
+ "moe_intermediate_size": 2048,
272
+ "mtp_loss_factor": 0.1,
273
+ "n_group": 1,
274
+ "n_routed_experts": 256,
275
+ "n_shared_experts": 1,
276
+ "norm_topk_prob": true,
277
+ "num_attention_heads": 64,
278
+ "num_experts_per_tok": 8,
279
+ "num_hidden_layers": 78,
280
+ "num_key_value_heads": 8,
281
+ "num_nextn_predict_layers": 1,
282
+ "pad_token_id": 120002,
283
+ "q_lora_rank": 2048,
284
+ "qk_head_dim": 256,
285
+ "qk_nope_head_dim": 192,
286
+ "qk_rope_head_dim": 64,
287
+ "rms_norm_eps": 1e-05,
288
+ "rope_parameters": {
289
+ "rope_theta": 10000000,
290
+ "rope_type": "default"
291
+ },
292
+ "routed_scaling_factor": 2.827,
293
+ "swiglu_limit": 10.0,
294
+ "tie_word_embeddings": false,
295
+ "topk_group": 1,
296
+ "transformers_version": "5.10.2",
297
+ "use_cache": true,
298
+ "use_dsa": true,
299
+ "use_mla": true,
300
+ "v_head_dim": 256,
301
+ "vocab_size": 120832,
302
+ "quantization_config": {
303
+ "quant_method": "modelopt",
304
+ "quantization": {
305
+ "quant_algo": "MXFP8",
306
+ "kv_cache_quant_algo": null,
307
+ "exclude_modules": [
308
+ "lm_head",
309
+ "model.embed_tokens",
310
+ "model.hc_head.hc_head_fn",
311
+ "model.layers.0.hc_attn_layer.hc_pre.hc_fn",
312
+ "model.layers.0.hc_mlp_layer.hc_pre.hc_fn",
313
+ "model.layers.0.self_attn.indexer.weights_proj",
314
+ "model.layers.0.self_attn.linear_gate",
315
+ "model.layers.1.hc_attn_layer.hc_pre.hc_fn",
316
+ "model.layers.1.hc_mlp_layer.hc_pre.hc_fn",
317
+ "model.layers.1.mlp.gate",
318
+ "model.layers.1.self_attn.indexer.weights_proj",
319
+ "model.layers.1.self_attn.linear_gate",
320
+ "model.layers.10.hc_attn_layer.hc_pre.hc_fn",
321
+ "model.layers.10.hc_mlp_layer.hc_pre.hc_fn",
322
+ "model.layers.10.mlp.gate",
323
+ "model.layers.10.self_attn.linear_gate",
324
+ "model.layers.11.hc_attn_layer.hc_pre.hc_fn",
325
+ "model.layers.11.hc_mlp_layer.hc_pre.hc_fn",
326
+ "model.layers.11.mlp.gate",
327
+ "model.layers.11.self_attn.linear_gate",
328
+ "model.layers.12.hc_attn_layer.hc_pre.hc_fn",
329
+ "model.layers.12.hc_mlp_layer.hc_pre.hc_fn",
330
+ "model.layers.12.mlp.gate",
331
+ "model.layers.12.self_attn.linear_gate",
332
+ "model.layers.13.hc_attn_layer.hc_pre.hc_fn",
333
+ "model.layers.13.hc_mlp_layer.hc_pre.hc_fn",
334
+ "model.layers.13.mlp.gate",
335
+ "model.layers.13.self_attn.indexer.weights_proj",
336
+ "model.layers.13.self_attn.linear_gate",
337
+ "model.layers.14.hc_attn_layer.hc_pre.hc_fn",
338
+ "model.layers.14.hc_mlp_layer.hc_pre.hc_fn",
339
+ "model.layers.14.mlp.gate",
340
+ "model.layers.14.self_attn.linear_gate",
341
+ "model.layers.15.hc_attn_layer.hc_pre.hc_fn",
342
+ "model.layers.15.hc_mlp_layer.hc_pre.hc_fn",
343
+ "model.layers.15.mlp.gate",
344
+ "model.layers.15.self_attn.linear_gate",
345
+ "model.layers.16.hc_attn_layer.hc_pre.hc_fn",
346
+ "model.layers.16.hc_mlp_layer.hc_pre.hc_fn",
347
+ "model.layers.16.mlp.gate",
348
+ "model.layers.16.self_attn.linear_gate",
349
+ "model.layers.17.hc_attn_layer.hc_pre.hc_fn",
350
+ "model.layers.17.hc_mlp_layer.hc_pre.hc_fn",
351
+ "model.layers.17.mlp.gate",
352
+ "model.layers.17.self_attn.indexer.weights_proj",
353
+ "model.layers.17.self_attn.linear_gate",
354
+ "model.layers.18.hc_attn_layer.hc_pre.hc_fn",
355
+ "model.layers.18.hc_mlp_layer.hc_pre.hc_fn",
356
+ "model.layers.18.mlp.gate",
357
+ "model.layers.18.self_attn.linear_gate",
358
+ "model.layers.19.hc_attn_layer.hc_pre.hc_fn",
359
+ "model.layers.19.hc_mlp_layer.hc_pre.hc_fn",
360
+ "model.layers.19.mlp.gate",
361
+ "model.layers.19.self_attn.linear_gate",
362
+ "model.layers.2.hc_attn_layer.hc_pre.hc_fn",
363
+ "model.layers.2.hc_mlp_layer.hc_pre.hc_fn",
364
+ "model.layers.2.mlp.gate",
365
+ "model.layers.2.self_attn.linear_gate",
366
+ "model.layers.20.hc_attn_layer.hc_pre.hc_fn",
367
+ "model.layers.20.hc_mlp_layer.hc_pre.hc_fn",
368
+ "model.layers.20.mlp.gate",
369
+ "model.layers.20.self_attn.linear_gate",
370
+ "model.layers.21.hc_attn_layer.hc_pre.hc_fn",
371
+ "model.layers.21.hc_mlp_layer.hc_pre.hc_fn",
372
+ "model.layers.21.mlp.gate",
373
+ "model.layers.21.self_attn.indexer.weights_proj",
374
+ "model.layers.21.self_attn.linear_gate",
375
+ "model.layers.22.hc_attn_layer.hc_pre.hc_fn",
376
+ "model.layers.22.hc_mlp_layer.hc_pre.hc_fn",
377
+ "model.layers.22.mlp.gate",
378
+ "model.layers.22.self_attn.linear_gate",
379
+ "model.layers.23.hc_attn_layer.hc_pre.hc_fn",
380
+ "model.layers.23.hc_mlp_layer.hc_pre.hc_fn",
381
+ "model.layers.23.mlp.gate",
382
+ "model.layers.23.self_attn.linear_gate",
383
+ "model.layers.24.hc_attn_layer.hc_pre.hc_fn",
384
+ "model.layers.24.hc_mlp_layer.hc_pre.hc_fn",
385
+ "model.layers.24.mlp.gate",
386
+ "model.layers.24.self_attn.linear_gate",
387
+ "model.layers.25.hc_attn_layer.hc_pre.hc_fn",
388
+ "model.layers.25.hc_mlp_layer.hc_pre.hc_fn",
389
+ "model.layers.25.mlp.gate",
390
+ "model.layers.25.self_attn.indexer.weights_proj",
391
+ "model.layers.25.self_attn.linear_gate",
392
+ "model.layers.26.hc_attn_layer.hc_pre.hc_fn",
393
+ "model.layers.26.hc_mlp_layer.hc_pre.hc_fn",
394
+ "model.layers.26.mlp.gate",
395
+ "model.layers.26.self_attn.linear_gate",
396
+ "model.layers.27.hc_attn_layer.hc_pre.hc_fn",
397
+ "model.layers.27.hc_mlp_layer.hc_pre.hc_fn",
398
+ "model.layers.27.mlp.gate",
399
+ "model.layers.27.self_attn.linear_gate",
400
+ "model.layers.28.hc_attn_layer.hc_pre.hc_fn",
401
+ "model.layers.28.hc_mlp_layer.hc_pre.hc_fn",
402
+ "model.layers.28.mlp.gate",
403
+ "model.layers.28.self_attn.linear_gate",
404
+ "model.layers.29.hc_attn_layer.hc_pre.hc_fn",
405
+ "model.layers.29.hc_mlp_layer.hc_pre.hc_fn",
406
+ "model.layers.29.mlp.gate",
407
+ "model.layers.29.self_attn.indexer.weights_proj",
408
+ "model.layers.29.self_attn.linear_gate",
409
+ "model.layers.3.hc_attn_layer.hc_pre.hc_fn",
410
+ "model.layers.3.hc_mlp_layer.hc_pre.hc_fn",
411
+ "model.layers.3.mlp.gate",
412
+ "model.layers.3.self_attn.linear_gate",
413
+ "model.layers.30.hc_attn_layer.hc_pre.hc_fn",
414
+ "model.layers.30.hc_mlp_layer.hc_pre.hc_fn",
415
+ "model.layers.30.mlp.gate",
416
+ "model.layers.30.self_attn.linear_gate",
417
+ "model.layers.31.hc_attn_layer.hc_pre.hc_fn",
418
+ "model.layers.31.hc_mlp_layer.hc_pre.hc_fn",
419
+ "model.layers.31.mlp.gate",
420
+ "model.layers.31.self_attn.linear_gate",
421
+ "model.layers.32.hc_attn_layer.hc_pre.hc_fn",
422
+ "model.layers.32.hc_mlp_layer.hc_pre.hc_fn",
423
+ "model.layers.32.mlp.gate",
424
+ "model.layers.32.self_attn.linear_gate",
425
+ "model.layers.33.hc_attn_layer.hc_pre.hc_fn",
426
+ "model.layers.33.hc_mlp_layer.hc_pre.hc_fn",
427
+ "model.layers.33.mlp.gate",
428
+ "model.layers.33.self_attn.indexer.weights_proj",
429
+ "model.layers.33.self_attn.linear_gate",
430
+ "model.layers.34.hc_attn_layer.hc_pre.hc_fn",
431
+ "model.layers.34.hc_mlp_layer.hc_pre.hc_fn",
432
+ "model.layers.34.mlp.gate",
433
+ "model.layers.34.self_attn.linear_gate",
434
+ "model.layers.35.hc_attn_layer.hc_pre.hc_fn",
435
+ "model.layers.35.hc_mlp_layer.hc_pre.hc_fn",
436
+ "model.layers.35.mlp.gate",
437
+ "model.layers.35.self_attn.linear_gate",
438
+ "model.layers.36.hc_attn_layer.hc_pre.hc_fn",
439
+ "model.layers.36.hc_mlp_layer.hc_pre.hc_fn",
440
+ "model.layers.36.mlp.gate",
441
+ "model.layers.36.self_attn.linear_gate",
442
+ "model.layers.37.hc_attn_layer.hc_pre.hc_fn",
443
+ "model.layers.37.hc_mlp_layer.hc_pre.hc_fn",
444
+ "model.layers.37.mlp.gate",
445
+ "model.layers.37.self_attn.indexer.weights_proj",
446
+ "model.layers.37.self_attn.linear_gate",
447
+ "model.layers.38.hc_attn_layer.hc_pre.hc_fn",
448
+ "model.layers.38.hc_mlp_layer.hc_pre.hc_fn",
449
+ "model.layers.38.mlp.gate",
450
+ "model.layers.38.self_attn.linear_gate",
451
+ "model.layers.39.hc_attn_layer.hc_pre.hc_fn",
452
+ "model.layers.39.hc_mlp_layer.hc_pre.hc_fn",
453
+ "model.layers.39.mlp.gate",
454
+ "model.layers.39.self_attn.linear_gate",
455
+ "model.layers.4.hc_attn_layer.hc_pre.hc_fn",
456
+ "model.layers.4.hc_mlp_layer.hc_pre.hc_fn",
457
+ "model.layers.4.mlp.gate",
458
+ "model.layers.4.self_attn.linear_gate",
459
+ "model.layers.40.hc_attn_layer.hc_pre.hc_fn",
460
+ "model.layers.40.hc_mlp_layer.hc_pre.hc_fn",
461
+ "model.layers.40.mlp.gate",
462
+ "model.layers.40.self_attn.linear_gate",
463
+ "model.layers.41.hc_attn_layer.hc_pre.hc_fn",
464
+ "model.layers.41.hc_mlp_layer.hc_pre.hc_fn",
465
+ "model.layers.41.mlp.gate",
466
+ "model.layers.41.self_attn.indexer.weights_proj",
467
+ "model.layers.41.self_attn.linear_gate",
468
+ "model.layers.42.hc_attn_layer.hc_pre.hc_fn",
469
+ "model.layers.42.hc_mlp_layer.hc_pre.hc_fn",
470
+ "model.layers.42.mlp.gate",
471
+ "model.layers.42.self_attn.linear_gate",
472
+ "model.layers.43.hc_attn_layer.hc_pre.hc_fn",
473
+ "model.layers.43.hc_mlp_layer.hc_pre.hc_fn",
474
+ "model.layers.43.mlp.gate",
475
+ "model.layers.43.self_attn.linear_gate",
476
+ "model.layers.44.hc_attn_layer.hc_pre.hc_fn",
477
+ "model.layers.44.hc_mlp_layer.hc_pre.hc_fn",
478
+ "model.layers.44.mlp.gate",
479
+ "model.layers.44.self_attn.linear_gate",
480
+ "model.layers.45.hc_attn_layer.hc_pre.hc_fn",
481
+ "model.layers.45.hc_mlp_layer.hc_pre.hc_fn",
482
+ "model.layers.45.mlp.gate",
483
+ "model.layers.45.self_attn.indexer.weights_proj",
484
+ "model.layers.45.self_attn.linear_gate",
485
+ "model.layers.46.hc_attn_layer.hc_pre.hc_fn",
486
+ "model.layers.46.hc_mlp_layer.hc_pre.hc_fn",
487
+ "model.layers.46.mlp.gate",
488
+ "model.layers.46.self_attn.linear_gate",
489
+ "model.layers.47.hc_attn_layer.hc_pre.hc_fn",
490
+ "model.layers.47.hc_mlp_layer.hc_pre.hc_fn",
491
+ "model.layers.47.mlp.gate",
492
+ "model.layers.47.self_attn.linear_gate",
493
+ "model.layers.48.hc_attn_layer.hc_pre.hc_fn",
494
+ "model.layers.48.hc_mlp_layer.hc_pre.hc_fn",
495
+ "model.layers.48.mlp.gate",
496
+ "model.layers.48.self_attn.linear_gate",
497
+ "model.layers.49.hc_attn_layer.hc_pre.hc_fn",
498
+ "model.layers.49.hc_mlp_layer.hc_pre.hc_fn",
499
+ "model.layers.49.mlp.gate",
500
+ "model.layers.49.self_attn.indexer.weights_proj",
501
+ "model.layers.49.self_attn.linear_gate",
502
+ "model.layers.5.hc_attn_layer.hc_pre.hc_fn",
503
+ "model.layers.5.hc_mlp_layer.hc_pre.hc_fn",
504
+ "model.layers.5.mlp.gate",
505
+ "model.layers.5.self_attn.indexer.weights_proj",
506
+ "model.layers.5.self_attn.linear_gate",
507
+ "model.layers.50.hc_attn_layer.hc_pre.hc_fn",
508
+ "model.layers.50.hc_mlp_layer.hc_pre.hc_fn",
509
+ "model.layers.50.mlp.gate",
510
+ "model.layers.50.self_attn.linear_gate",
511
+ "model.layers.51.hc_attn_layer.hc_pre.hc_fn",
512
+ "model.layers.51.hc_mlp_layer.hc_pre.hc_fn",
513
+ "model.layers.51.mlp.gate",
514
+ "model.layers.51.self_attn.linear_gate",
515
+ "model.layers.52.hc_attn_layer.hc_pre.hc_fn",
516
+ "model.layers.52.hc_mlp_layer.hc_pre.hc_fn",
517
+ "model.layers.52.mlp.gate",
518
+ "model.layers.52.self_attn.linear_gate",
519
+ "model.layers.53.hc_attn_layer.hc_pre.hc_fn",
520
+ "model.layers.53.hc_mlp_layer.hc_pre.hc_fn",
521
+ "model.layers.53.mlp.gate",
522
+ "model.layers.53.self_attn.indexer.weights_proj",
523
+ "model.layers.53.self_attn.linear_gate",
524
+ "model.layers.54.hc_attn_layer.hc_pre.hc_fn",
525
+ "model.layers.54.hc_mlp_layer.hc_pre.hc_fn",
526
+ "model.layers.54.mlp.gate",
527
+ "model.layers.54.self_attn.linear_gate",
528
+ "model.layers.55.hc_attn_layer.hc_pre.hc_fn",
529
+ "model.layers.55.hc_mlp_layer.hc_pre.hc_fn",
530
+ "model.layers.55.mlp.gate",
531
+ "model.layers.55.self_attn.linear_gate",
532
+ "model.layers.56.hc_attn_layer.hc_pre.hc_fn",
533
+ "model.layers.56.hc_mlp_layer.hc_pre.hc_fn",
534
+ "model.layers.56.mlp.gate",
535
+ "model.layers.56.self_attn.linear_gate",
536
+ "model.layers.57.hc_attn_layer.hc_pre.hc_fn",
537
+ "model.layers.57.hc_mlp_layer.hc_pre.hc_fn",
538
+ "model.layers.57.mlp.gate",
539
+ "model.layers.57.self_attn.indexer.weights_proj",
540
+ "model.layers.57.self_attn.linear_gate",
541
+ "model.layers.58.hc_attn_layer.hc_pre.hc_fn",
542
+ "model.layers.58.hc_mlp_layer.hc_pre.hc_fn",
543
+ "model.layers.58.mlp.gate",
544
+ "model.layers.58.self_attn.linear_gate",
545
+ "model.layers.59.hc_attn_layer.hc_pre.hc_fn",
546
+ "model.layers.59.hc_mlp_layer.hc_pre.hc_fn",
547
+ "model.layers.59.mlp.gate",
548
+ "model.layers.59.self_attn.linear_gate",
549
+ "model.layers.6.hc_attn_layer.hc_pre.hc_fn",
550
+ "model.layers.6.hc_mlp_layer.hc_pre.hc_fn",
551
+ "model.layers.6.mlp.gate",
552
+ "model.layers.6.self_attn.linear_gate",
553
+ "model.layers.60.hc_attn_layer.hc_pre.hc_fn",
554
+ "model.layers.60.hc_mlp_layer.hc_pre.hc_fn",
555
+ "model.layers.60.mlp.gate",
556
+ "model.layers.60.self_attn.linear_gate",
557
+ "model.layers.61.hc_attn_layer.hc_pre.hc_fn",
558
+ "model.layers.61.hc_mlp_layer.hc_pre.hc_fn",
559
+ "model.layers.61.mlp.gate",
560
+ "model.layers.61.self_attn.indexer.weights_proj",
561
+ "model.layers.61.self_attn.linear_gate",
562
+ "model.layers.62.hc_attn_layer.hc_pre.hc_fn",
563
+ "model.layers.62.hc_mlp_layer.hc_pre.hc_fn",
564
+ "model.layers.62.mlp.gate",
565
+ "model.layers.62.self_attn.linear_gate",
566
+ "model.layers.63.hc_attn_layer.hc_pre.hc_fn",
567
+ "model.layers.63.hc_mlp_layer.hc_pre.hc_fn",
568
+ "model.layers.63.mlp.gate",
569
+ "model.layers.63.self_attn.linear_gate",
570
+ "model.layers.64.hc_attn_layer.hc_pre.hc_fn",
571
+ "model.layers.64.hc_mlp_layer.hc_pre.hc_fn",
572
+ "model.layers.64.mlp.gate",
573
+ "model.layers.64.self_attn.linear_gate",
574
+ "model.layers.65.hc_attn_layer.hc_pre.hc_fn",
575
+ "model.layers.65.hc_mlp_layer.hc_pre.hc_fn",
576
+ "model.layers.65.mlp.gate",
577
+ "model.layers.65.self_attn.indexer.weights_proj",
578
+ "model.layers.65.self_attn.linear_gate",
579
+ "model.layers.66.hc_attn_layer.hc_pre.hc_fn",
580
+ "model.layers.66.hc_mlp_layer.hc_pre.hc_fn",
581
+ "model.layers.66.mlp.gate",
582
+ "model.layers.66.self_attn.linear_gate",
583
+ "model.layers.67.hc_attn_layer.hc_pre.hc_fn",
584
+ "model.layers.67.hc_mlp_layer.hc_pre.hc_fn",
585
+ "model.layers.67.mlp.gate",
586
+ "model.layers.67.self_attn.linear_gate",
587
+ "model.layers.68.hc_attn_layer.hc_pre.hc_fn",
588
+ "model.layers.68.hc_mlp_layer.hc_pre.hc_fn",
589
+ "model.layers.68.mlp.gate",
590
+ "model.layers.68.self_attn.linear_gate",
591
+ "model.layers.69.hc_attn_layer.hc_pre.hc_fn",
592
+ "model.layers.69.hc_mlp_layer.hc_pre.hc_fn",
593
+ "model.layers.69.mlp.gate",
594
+ "model.layers.69.self_attn.indexer.weights_proj",
595
+ "model.layers.69.self_attn.linear_gate",
596
+ "model.layers.7.hc_attn_layer.hc_pre.hc_fn",
597
+ "model.layers.7.hc_mlp_layer.hc_pre.hc_fn",
598
+ "model.layers.7.mlp.gate",
599
+ "model.layers.7.self_attn.linear_gate",
600
+ "model.layers.70.hc_attn_layer.hc_pre.hc_fn",
601
+ "model.layers.70.hc_mlp_layer.hc_pre.hc_fn",
602
+ "model.layers.70.mlp.gate",
603
+ "model.layers.70.self_attn.linear_gate",
604
+ "model.layers.71.hc_attn_layer.hc_pre.hc_fn",
605
+ "model.layers.71.hc_mlp_layer.hc_pre.hc_fn",
606
+ "model.layers.71.mlp.gate",
607
+ "model.layers.71.self_attn.linear_gate",
608
+ "model.layers.72.hc_attn_layer.hc_pre.hc_fn",
609
+ "model.layers.72.hc_mlp_layer.hc_pre.hc_fn",
610
+ "model.layers.72.mlp.gate",
611
+ "model.layers.72.self_attn.linear_gate",
612
+ "model.layers.73.hc_attn_layer.hc_pre.hc_fn",
613
+ "model.layers.73.hc_mlp_layer.hc_pre.hc_fn",
614
+ "model.layers.73.mlp.gate",
615
+ "model.layers.73.self_attn.indexer.weights_proj",
616
+ "model.layers.73.self_attn.linear_gate",
617
+ "model.layers.74.hc_attn_layer.hc_pre.hc_fn",
618
+ "model.layers.74.hc_mlp_layer.hc_pre.hc_fn",
619
+ "model.layers.74.mlp.gate",
620
+ "model.layers.74.self_attn.linear_gate",
621
+ "model.layers.75.hc_attn_layer.hc_pre.hc_fn",
622
+ "model.layers.75.hc_mlp_layer.hc_pre.hc_fn",
623
+ "model.layers.75.mlp.gate",
624
+ "model.layers.75.self_attn.linear_gate",
625
+ "model.layers.76.hc_attn_layer.hc_pre.hc_fn",
626
+ "model.layers.76.hc_mlp_layer.hc_pre.hc_fn",
627
+ "model.layers.76.mlp.gate",
628
+ "model.layers.76.self_attn.linear_gate",
629
+ "model.layers.77.hc_attn_layer.hc_pre.hc_fn",
630
+ "model.layers.77.hc_mlp_layer.hc_pre.hc_fn",
631
+ "model.layers.77.mlp.gate",
632
+ "model.layers.77.self_attn.indexer.weights_proj",
633
+ "model.layers.77.self_attn.linear_gate",
634
+ "model.layers.8.hc_attn_layer.hc_pre.hc_fn",
635
+ "model.layers.8.hc_mlp_layer.hc_pre.hc_fn",
636
+ "model.layers.8.mlp.gate",
637
+ "model.layers.8.self_attn.linear_gate",
638
+ "model.layers.9.hc_attn_layer.hc_pre.hc_fn",
639
+ "model.layers.9.hc_mlp_layer.hc_pre.hc_fn",
640
+ "model.layers.9.mlp.gate",
641
+ "model.layers.9.self_attn.indexer.weights_proj",
642
+ "model.layers.9.self_attn.linear_gate",
643
+ "model.mtp_layers.0.eh_proj",
644
+ "model.mtp_layers.0.mlp.gate",
645
+ "model.mtp_layers.0.self_attn.indexer.weights_proj",
646
+ "model.mtp_layers.0.self_attn.linear_gate"
647
+ ]
648
+ }
649
+ },
650
+ "torch_dtype": "bfloat16"
651
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 120000,
3
+ "do_sample": true,
4
+ "eos_token_id": 120025,
5
+ "pad_token_id": 120002,
6
+ "temperature": 0.9,
7
+ "top_k": -1,
8
+ "top_p": 1,
9
+ "transformers_version": "5.10.2"
10
+ }
model-00001-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414cc8c59bcfd545fe46b63ad31028af39a487df7a1fc837e0e950214b308979
3
+ size 9965666800
model-00002-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8396df203fc1e77e3e25b8a111b93027d20f83a8455c0e0dec63a0d562c042
3
+ size 9965666808
model-00003-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626fe3712d65c468c6c603d9df0e9aed95f7704caad2f31d03375b3c1dbf6bb9
3
+ size 9965666808
model-00004-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57d8faefe9e3f62b62e2577745fe975478a838726a1968d920eeb5f08d1b659
3
+ size 9965666800
model-00005-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a430997c16e724f83e564a61fa70009a60dbe0c9c2aeb1f2514197382e85675d
3
+ size 9965666808
model-00006-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c5ebbf103e6aa5ff0c67b66c1daed70c36cc5d75f6777e7932683460b1b7fe
3
+ size 9965666808
model-00007-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfae267c634535d61c32abec63f88d6e4ea0d4516f8a8effedb6c18d32fede2c
3
+ size 9965666800
model-00008-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d9521edc9842610d0e6847116af715b834588bae0f685ca6ad7d58d15d6c0d
3
+ size 9965666808
model-00009-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be75396790490279d1d2beb0e04fde101ef75915cf1d04cd483258e923f3cdd
3
+ size 9965666808
model-00010-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43085db3067c7133f9f4131384f21bda57e561bf6af6908d81765ae18e7b980
3
+ size 9965666800
model-00011-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54af493cca42fadbbbe4479c3bd832281da7aa839920073fc84c6c8d25ec8690
3
+ size 9965666808
model-00012-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0c0f158c84b3744acc312dd31b687bdcc4870c40aa70ffcdf8b13048b17c53
3
+ size 9965666808
model-00013-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100a06a52c0aef50c33b24322bf47236c18503b1512d0de428c6ed36a7a3046b
3
+ size 9965666800
model-00014-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2c7f73dff160e0996c0017897d04a7e07f183b7fc85e12091eed76233e6956
3
+ size 9965666808
model-00015-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b978107037f67a85f66819b3d7eadf4ddf84059d6095fc186431dc495a60a5fa
3
+ size 9965666808
model-00016-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a3d99130ba6c50d2dc0af6c27029752757ee9edd357ea84ae50510fb781073
3
+ size 9965666800
model-00017-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d1bc6843dcfa873b9705e020267fedb5b79384a10f6f57a3424c528998d5ed
3
+ size 9965666808
model-00018-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd84de448c8b6cd26e87427fddcee28ca925e1287e5d3a6503c1430d05f6a17
3
+ size 9965666808
model-00019-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451e4caefc5d86b444e64e1eadd3128a5e7c9528ac02ba220603cae19a137d8f
3
+ size 9965666800
model-00020-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278e4c635a9b7c44e48bac5da5fb217a33cd44c8c5268de04cd97a354879b230
3
+ size 9965666808
model-00021-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4185e4eb6b6a88faded960d902b38f8f908e48630f21d27104434c054a06150f
3
+ size 9965666808
model-00022-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef96e10d9c683a5718eb9ff475b25321852254a0e8c7d6398e3a7548ada9821
3
+ size 9965666800
model-00023-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909676a743fd94c95c78112a42a22cd24dd94a218a26681d43d152c7fe93f5ea
3
+ size 9965666808
model-00024-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722eac11890368bec6b258cc09e4a4581879a286cf811c76177af6800d57471d
3
+ size 9965666808
model-00025-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa641469e0d210930d75b0f366afb3a08a00de27282b7b8ba5e55aac64904344
3
+ size 9965666800
model-00026-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a29db98b926f746ffd67fa66de1f1b443628d2e9436ba032905aa0785e094fc
3
+ size 9965666808
model-00027-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a158e22416bff4f3bf4b8769f550dde35c05efc9281c499717060214f5b30b65
3
+ size 9965666808
model-00028-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612ff15c3c9dbd4242e6b5c4be6eeffb874f9a440bd394e344a7935ffe94210e
3
+ size 9965666808
model-00029-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681c9d57cc4d58f389f9f1d15fe9c4a612399e46c78e3a7658415346cc507626
3
+ size 9965666808
model-00030-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620cb4be7f182244cb8d85b4578a72445117cba32c1139917c7d58ac19d82e78
3
+ size 9965666808
model-00031-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc95523478aaac7c431502cf888480792ef7e4162b5ded83c9a5fe5b970f86d
3
+ size 9965666808
model-00032-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a0c1fab7e1eb6446be1b366b425ca055b260158a55f513431f9247aa7da61e
3
+ size 9965666808
model-00033-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451f000728d0bf9caf0302423bdc148e1083be39f6b948b26da850108db07f18
3
+ size 9965666808
model-00034-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9a1604006bbe07f0dc66efbf8a3e0b21ed53ed6f89389e47fc05b39c059c97
3
+ size 9965666808
model-00035-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1746e8a11fdc5fd391ac80b16545ffaa6cb29682850eaf50c024e2244776659e
3
+ size 9965666808
model-00036-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e333786190b0cb378f769fb46ef0dcf41f480201500ee2fbc9e337f0ea695348
3
+ size 9965666808
model-00037-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1276412b7145ca2bf361ab8c1fa98dc62595a976c98e81088efca06e5c343048
3
+ size 9965666808
model-00038-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f75ea0670ee6995e86e60b1da6ed5553126e794358d73bc4f49f8facfb266fb
3
+ size 9965666808
model-00039-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84f35f54f413c99b702f1c7b6428e5ca59dba86f70c72202d662cd2f21d00b0
3
+ size 9965666808
model-00040-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21667ff5533397d947e4b7a6d509f2303862f730a0cb1442bd210f0c76e6a77
3
+ size 9965666808
model-00041-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9283bdabf3634c64344983215b4fd15e52522149fed0400a6cf9d8dc841e23d3
3
+ size 9965666808
model-00042-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257e798baeb95453b2f6aed635e40164509ced129340d38ce6dcb8bfb643f372
3
+ size 9965666808
model-00043-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77aa529f077bb414b1a33e57fc2d98046a87346109477f89a054b633957ccd5c
3
+ size 9965666808
model-00044-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d498e565f1b7e230f09401fdc484a01ab86e0a95a39ff56d40f0dd93ed2bc0
3
+ size 9965666808
model-00045-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e569e3260dda178ef2e180b32c423ebf8d36b173be4600b84c59d05f63f97482
3
+ size 9965666808
model-00046-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f79e1d0aec4238a577d29da2638c43b0c5a94090255fd96bea1ea0ce0ef97b
3
+ size 1484783728
model-00047-of-00130.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5788bd231c8e0ffdd7454568e088be1cd0e723d53b6c657fe55a6334baf0d08
3
+ size 714081224