Upload folder using huggingface_hub
Browse files- chat_template.jinja +15 -22
- config.json +1 -1
- model.safetensors.index.json +500 -500
- model-mtp.safetensors → mtp.safetensors +0 -0
- tokenizer_config.json +1 -1
chat_template.jinja
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
-
{#
|
|
|
|
| 2 |
{%- if tools -%}
|
| 3 |
<|system|>
|
| 4 |
# Tools
|
|
@@ -43,25 +44,19 @@ For each function call, output the function name and arguments within the follow
|
|
| 43 |
{%- endfor %}
|
| 44 |
{% for m in messages %}
|
| 45 |
{%- if m.role == 'user' -%}<|user|>
|
| 46 |
-
{
|
| 47 |
-
{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not content.endswith("/nothink")) else '' -}}
|
| 48 |
{%- elif m.role == 'assistant' -%}
|
| 49 |
<|assistant|>
|
| 50 |
{%- set reasoning_content = '' %}
|
| 51 |
-
{%- set content = visible_text(m.content)
|
| 52 |
-
{%- if m.reasoning_content is
|
| 53 |
{%- set reasoning_content = m.reasoning_content %}
|
| 54 |
{%- else %}
|
| 55 |
-
{
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
{%- set reasoning_content = (part.split("<think>")|last) %}
|
| 60 |
-
{%- set reasoning_content = reasoning_content.lstrip('\n').rstrip('\n') -%}
|
| 61 |
-
{%- else -%}
|
| 62 |
-
{%- set content = part.lstrip('\n') %}
|
| 63 |
-
{%- endif %}
|
| 64 |
-
{%- endfor %}
|
| 65 |
{%- endif %}
|
| 66 |
{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
|
| 67 |
{{ '\n<think>' + reasoning_content.strip() + '</think>'}}
|
|
@@ -77,14 +72,11 @@ For each function call, output the function name and arguments within the follow
|
|
| 77 |
{%- set tc = tc.function %}
|
| 78 |
{%- endif %}
|
| 79 |
{{ '\n<tool_call>' + tc.name }}
|
| 80 |
-
{% set _args = tc.arguments %}
|
| 81 |
-
{%- if _args is not mapping -%}
|
| 82 |
-
{%- set _args = {} %}
|
| 83 |
-
{%- endif -%}
|
| 84 |
{% for k, v in _args|items %}
|
| 85 |
<arg_key>{{ k }}</arg_key>
|
| 86 |
<arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>
|
| 87 |
-
{% endfor %}
|
| 88 |
</tool_call>{% endfor %}
|
| 89 |
{% endif %}
|
| 90 |
{%- elif m.role == 'tool' -%}
|
|
@@ -104,9 +96,10 @@ For each function call, output the function name and arguments within the follow
|
|
| 104 |
{% endif -%}
|
| 105 |
{%- elif m.role == 'system' -%}
|
| 106 |
<|system|>
|
| 107 |
-
{{ visible_text(m.content)
|
| 108 |
{%- endif -%}
|
| 109 |
{%- endfor -%}
|
| 110 |
{%- if add_generation_prompt -%}
|
| 111 |
<|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
|
| 112 |
-
{%- endif -%}
|
|
|
|
|
|
| 1 |
+
{# Unsloth template fixes #}
|
| 2 |
+
[gMASK]<sop>
|
| 3 |
{%- if tools -%}
|
| 4 |
<|system|>
|
| 5 |
# Tools
|
|
|
|
| 44 |
{%- endfor %}
|
| 45 |
{% for m in messages %}
|
| 46 |
{%- if m.role == 'user' -%}<|user|>
|
| 47 |
+
{{ visible_text(m.content) }}
|
| 48 |
+
{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
|
| 49 |
{%- elif m.role == 'assistant' -%}
|
| 50 |
<|assistant|>
|
| 51 |
{%- set reasoning_content = '' %}
|
| 52 |
+
{%- set content = visible_text(m.content) %}
|
| 53 |
+
{%- if m.reasoning_content is string %}
|
| 54 |
{%- set reasoning_content = m.reasoning_content %}
|
| 55 |
{%- else %}
|
| 56 |
+
{%- if '</think>' in content %}
|
| 57 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 58 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 59 |
+
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
{%- endif %}
|
| 61 |
{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
|
| 62 |
{{ '\n<think>' + reasoning_content.strip() + '</think>'}}
|
|
|
|
| 72 |
{%- set tc = tc.function %}
|
| 73 |
{%- endif %}
|
| 74 |
{{ '\n<tool_call>' + tc.name }}
|
| 75 |
+
{% set _args = tc.arguments %}{%- if _args is mapping %}
|
|
|
|
|
|
|
|
|
|
| 76 |
{% for k, v in _args|items %}
|
| 77 |
<arg_key>{{ k }}</arg_key>
|
| 78 |
<arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>
|
| 79 |
+
{% endfor %}{%- endif %}
|
| 80 |
</tool_call>{% endfor %}
|
| 81 |
{% endif %}
|
| 82 |
{%- elif m.role == 'tool' -%}
|
|
|
|
| 96 |
{% endif -%}
|
| 97 |
{%- elif m.role == 'system' -%}
|
| 98 |
<|system|>
|
| 99 |
+
{{ visible_text(m.content) }}
|
| 100 |
{%- endif -%}
|
| 101 |
{%- endfor -%}
|
| 102 |
{%- if add_generation_prompt -%}
|
| 103 |
<|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
|
| 104 |
+
{%- endif -%}
|
| 105 |
+
{# Copyright 2025-present Unsloth. Apache 2.0 License. #}
|
config.json
CHANGED
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"routed_scaling_factor": 2.5,
|
| 37 |
"tie_word_embeddings": false,
|
| 38 |
"topk_group": 1,
|
| 39 |
-
"transformers_version": "4.
|
| 40 |
"unsloth_fixed": true,
|
| 41 |
"use_cache": true,
|
| 42 |
"use_qk_norm": true,
|
|
|
|
| 36 |
"routed_scaling_factor": 2.5,
|
| 37 |
"tie_word_embeddings": false,
|
| 38 |
"topk_group": 1,
|
| 39 |
+
"transformers_version": "4.57.3",
|
| 40 |
"unsloth_fixed": true,
|
| 41 |
"use_cache": true,
|
| 42 |
"use_qk_norm": true,
|
model.safetensors.index.json
CHANGED
|
@@ -44192,505 +44192,505 @@
|
|
| 44192 |
"model.layers.91.self_attn.v_proj.bias": "model-00092-of-00092.safetensors",
|
| 44193 |
"model.layers.91.self_attn.v_proj.weight": "model-00092-of-00092.safetensors",
|
| 44194 |
"model.norm.weight": "model-00092-of-00092.safetensors",
|
| 44195 |
-
"model.layers.92.eh_proj.weight": "
|
| 44196 |
-
"model.layers.92.enorm.weight": "
|
| 44197 |
-
"model.layers.92.hnorm.weight": "
|
| 44198 |
-
"model.layers.92.input_layernorm.weight": "
|
| 44199 |
-
"model.layers.92.mlp.experts.0.down_proj.weight": "
|
| 44200 |
-
"model.layers.92.mlp.experts.0.gate_proj.weight": "
|
| 44201 |
-
"model.layers.92.mlp.experts.0.up_proj.weight": "
|
| 44202 |
-
"model.layers.92.mlp.experts.1.down_proj.weight": "
|
| 44203 |
-
"model.layers.92.mlp.experts.1.gate_proj.weight": "
|
| 44204 |
-
"model.layers.92.mlp.experts.1.up_proj.weight": "
|
| 44205 |
-
"model.layers.92.mlp.experts.10.down_proj.weight": "
|
| 44206 |
-
"model.layers.92.mlp.experts.10.gate_proj.weight": "
|
| 44207 |
-
"model.layers.92.mlp.experts.10.up_proj.weight": "
|
| 44208 |
-
"model.layers.92.mlp.experts.100.down_proj.weight": "
|
| 44209 |
-
"model.layers.92.mlp.experts.100.gate_proj.weight": "
|
| 44210 |
-
"model.layers.92.mlp.experts.100.up_proj.weight": "
|
| 44211 |
-
"model.layers.92.mlp.experts.101.down_proj.weight": "
|
| 44212 |
-
"model.layers.92.mlp.experts.101.gate_proj.weight": "
|
| 44213 |
-
"model.layers.92.mlp.experts.101.up_proj.weight": "
|
| 44214 |
-
"model.layers.92.mlp.experts.102.down_proj.weight": "
|
| 44215 |
-
"model.layers.92.mlp.experts.102.gate_proj.weight": "
|
| 44216 |
-
"model.layers.92.mlp.experts.102.up_proj.weight": "
|
| 44217 |
-
"model.layers.92.mlp.experts.103.down_proj.weight": "
|
| 44218 |
-
"model.layers.92.mlp.experts.103.gate_proj.weight": "
|
| 44219 |
-
"model.layers.92.mlp.experts.103.up_proj.weight": "
|
| 44220 |
-
"model.layers.92.mlp.experts.104.down_proj.weight": "
|
| 44221 |
-
"model.layers.92.mlp.experts.104.gate_proj.weight": "
|
| 44222 |
-
"model.layers.92.mlp.experts.104.up_proj.weight": "
|
| 44223 |
-
"model.layers.92.mlp.experts.105.down_proj.weight": "
|
| 44224 |
-
"model.layers.92.mlp.experts.105.gate_proj.weight": "
|
| 44225 |
-
"model.layers.92.mlp.experts.105.up_proj.weight": "
|
| 44226 |
-
"model.layers.92.mlp.experts.106.down_proj.weight": "
|
| 44227 |
-
"model.layers.92.mlp.experts.106.gate_proj.weight": "
|
| 44228 |
-
"model.layers.92.mlp.experts.106.up_proj.weight": "
|
| 44229 |
-
"model.layers.92.mlp.experts.107.down_proj.weight": "
|
| 44230 |
-
"model.layers.92.mlp.experts.107.gate_proj.weight": "
|
| 44231 |
-
"model.layers.92.mlp.experts.107.up_proj.weight": "
|
| 44232 |
-
"model.layers.92.mlp.experts.108.down_proj.weight": "
|
| 44233 |
-
"model.layers.92.mlp.experts.108.gate_proj.weight": "
|
| 44234 |
-
"model.layers.92.mlp.experts.108.up_proj.weight": "
|
| 44235 |
-
"model.layers.92.mlp.experts.109.down_proj.weight": "
|
| 44236 |
-
"model.layers.92.mlp.experts.109.gate_proj.weight": "
|
| 44237 |
-
"model.layers.92.mlp.experts.109.up_proj.weight": "
|
| 44238 |
-
"model.layers.92.mlp.experts.11.down_proj.weight": "
|
| 44239 |
-
"model.layers.92.mlp.experts.11.gate_proj.weight": "
|
| 44240 |
-
"model.layers.92.mlp.experts.11.up_proj.weight": "
|
| 44241 |
-
"model.layers.92.mlp.experts.110.down_proj.weight": "
|
| 44242 |
-
"model.layers.92.mlp.experts.110.gate_proj.weight": "
|
| 44243 |
-
"model.layers.92.mlp.experts.110.up_proj.weight": "
|
| 44244 |
-
"model.layers.92.mlp.experts.111.down_proj.weight": "
|
| 44245 |
-
"model.layers.92.mlp.experts.111.gate_proj.weight": "
|
| 44246 |
-
"model.layers.92.mlp.experts.111.up_proj.weight": "
|
| 44247 |
-
"model.layers.92.mlp.experts.112.down_proj.weight": "
|
| 44248 |
-
"model.layers.92.mlp.experts.112.gate_proj.weight": "
|
| 44249 |
-
"model.layers.92.mlp.experts.112.up_proj.weight": "
|
| 44250 |
-
"model.layers.92.mlp.experts.113.down_proj.weight": "
|
| 44251 |
-
"model.layers.92.mlp.experts.113.gate_proj.weight": "
|
| 44252 |
-
"model.layers.92.mlp.experts.113.up_proj.weight": "
|
| 44253 |
-
"model.layers.92.mlp.experts.114.down_proj.weight": "
|
| 44254 |
-
"model.layers.92.mlp.experts.114.gate_proj.weight": "
|
| 44255 |
-
"model.layers.92.mlp.experts.114.up_proj.weight": "
|
| 44256 |
-
"model.layers.92.mlp.experts.115.down_proj.weight": "
|
| 44257 |
-
"model.layers.92.mlp.experts.115.gate_proj.weight": "
|
| 44258 |
-
"model.layers.92.mlp.experts.115.up_proj.weight": "
|
| 44259 |
-
"model.layers.92.mlp.experts.116.down_proj.weight": "
|
| 44260 |
-
"model.layers.92.mlp.experts.116.gate_proj.weight": "
|
| 44261 |
-
"model.layers.92.mlp.experts.116.up_proj.weight": "
|
| 44262 |
-
"model.layers.92.mlp.experts.117.down_proj.weight": "
|
| 44263 |
-
"model.layers.92.mlp.experts.117.gate_proj.weight": "
|
| 44264 |
-
"model.layers.92.mlp.experts.117.up_proj.weight": "
|
| 44265 |
-
"model.layers.92.mlp.experts.118.down_proj.weight": "
|
| 44266 |
-
"model.layers.92.mlp.experts.118.gate_proj.weight": "
|
| 44267 |
-
"model.layers.92.mlp.experts.118.up_proj.weight": "
|
| 44268 |
-
"model.layers.92.mlp.experts.119.down_proj.weight": "
|
| 44269 |
-
"model.layers.92.mlp.experts.119.gate_proj.weight": "
|
| 44270 |
-
"model.layers.92.mlp.experts.119.up_proj.weight": "
|
| 44271 |
-
"model.layers.92.mlp.experts.12.down_proj.weight": "
|
| 44272 |
-
"model.layers.92.mlp.experts.12.gate_proj.weight": "
|
| 44273 |
-
"model.layers.92.mlp.experts.12.up_proj.weight": "
|
| 44274 |
-
"model.layers.92.mlp.experts.120.down_proj.weight": "
|
| 44275 |
-
"model.layers.92.mlp.experts.120.gate_proj.weight": "
|
| 44276 |
-
"model.layers.92.mlp.experts.120.up_proj.weight": "
|
| 44277 |
-
"model.layers.92.mlp.experts.121.down_proj.weight": "
|
| 44278 |
-
"model.layers.92.mlp.experts.121.gate_proj.weight": "
|
| 44279 |
-
"model.layers.92.mlp.experts.121.up_proj.weight": "
|
| 44280 |
-
"model.layers.92.mlp.experts.122.down_proj.weight": "
|
| 44281 |
-
"model.layers.92.mlp.experts.122.gate_proj.weight": "
|
| 44282 |
-
"model.layers.92.mlp.experts.122.up_proj.weight": "
|
| 44283 |
-
"model.layers.92.mlp.experts.123.down_proj.weight": "
|
| 44284 |
-
"model.layers.92.mlp.experts.123.gate_proj.weight": "
|
| 44285 |
-
"model.layers.92.mlp.experts.123.up_proj.weight": "
|
| 44286 |
-
"model.layers.92.mlp.experts.124.down_proj.weight": "
|
| 44287 |
-
"model.layers.92.mlp.experts.124.gate_proj.weight": "
|
| 44288 |
-
"model.layers.92.mlp.experts.124.up_proj.weight": "
|
| 44289 |
-
"model.layers.92.mlp.experts.125.down_proj.weight": "
|
| 44290 |
-
"model.layers.92.mlp.experts.125.gate_proj.weight": "
|
| 44291 |
-
"model.layers.92.mlp.experts.125.up_proj.weight": "
|
| 44292 |
-
"model.layers.92.mlp.experts.126.down_proj.weight": "
|
| 44293 |
-
"model.layers.92.mlp.experts.126.gate_proj.weight": "
|
| 44294 |
-
"model.layers.92.mlp.experts.126.up_proj.weight": "
|
| 44295 |
-
"model.layers.92.mlp.experts.127.down_proj.weight": "
|
| 44296 |
-
"model.layers.92.mlp.experts.127.gate_proj.weight": "
|
| 44297 |
-
"model.layers.92.mlp.experts.127.up_proj.weight": "
|
| 44298 |
-
"model.layers.92.mlp.experts.128.down_proj.weight": "
|
| 44299 |
-
"model.layers.92.mlp.experts.128.gate_proj.weight": "
|
| 44300 |
-
"model.layers.92.mlp.experts.128.up_proj.weight": "
|
| 44301 |
-
"model.layers.92.mlp.experts.129.down_proj.weight": "
|
| 44302 |
-
"model.layers.92.mlp.experts.129.gate_proj.weight": "
|
| 44303 |
-
"model.layers.92.mlp.experts.129.up_proj.weight": "
|
| 44304 |
-
"model.layers.92.mlp.experts.13.down_proj.weight": "
|
| 44305 |
-
"model.layers.92.mlp.experts.13.gate_proj.weight": "
|
| 44306 |
-
"model.layers.92.mlp.experts.13.up_proj.weight": "
|
| 44307 |
-
"model.layers.92.mlp.experts.130.down_proj.weight": "
|
| 44308 |
-
"model.layers.92.mlp.experts.130.gate_proj.weight": "
|
| 44309 |
-
"model.layers.92.mlp.experts.130.up_proj.weight": "
|
| 44310 |
-
"model.layers.92.mlp.experts.131.down_proj.weight": "
|
| 44311 |
-
"model.layers.92.mlp.experts.131.gate_proj.weight": "
|
| 44312 |
-
"model.layers.92.mlp.experts.131.up_proj.weight": "
|
| 44313 |
-
"model.layers.92.mlp.experts.132.down_proj.weight": "
|
| 44314 |
-
"model.layers.92.mlp.experts.132.gate_proj.weight": "
|
| 44315 |
-
"model.layers.92.mlp.experts.132.up_proj.weight": "
|
| 44316 |
-
"model.layers.92.mlp.experts.133.down_proj.weight": "
|
| 44317 |
-
"model.layers.92.mlp.experts.133.gate_proj.weight": "
|
| 44318 |
-
"model.layers.92.mlp.experts.133.up_proj.weight": "
|
| 44319 |
-
"model.layers.92.mlp.experts.134.down_proj.weight": "
|
| 44320 |
-
"model.layers.92.mlp.experts.134.gate_proj.weight": "
|
| 44321 |
-
"model.layers.92.mlp.experts.134.up_proj.weight": "
|
| 44322 |
-
"model.layers.92.mlp.experts.135.down_proj.weight": "
|
| 44323 |
-
"model.layers.92.mlp.experts.135.gate_proj.weight": "
|
| 44324 |
-
"model.layers.92.mlp.experts.135.up_proj.weight": "
|
| 44325 |
-
"model.layers.92.mlp.experts.136.down_proj.weight": "
|
| 44326 |
-
"model.layers.92.mlp.experts.136.gate_proj.weight": "
|
| 44327 |
-
"model.layers.92.mlp.experts.136.up_proj.weight": "
|
| 44328 |
-
"model.layers.92.mlp.experts.137.down_proj.weight": "
|
| 44329 |
-
"model.layers.92.mlp.experts.137.gate_proj.weight": "
|
| 44330 |
-
"model.layers.92.mlp.experts.137.up_proj.weight": "
|
| 44331 |
-
"model.layers.92.mlp.experts.138.down_proj.weight": "
|
| 44332 |
-
"model.layers.92.mlp.experts.138.gate_proj.weight": "
|
| 44333 |
-
"model.layers.92.mlp.experts.138.up_proj.weight": "
|
| 44334 |
-
"model.layers.92.mlp.experts.139.down_proj.weight": "
|
| 44335 |
-
"model.layers.92.mlp.experts.139.gate_proj.weight": "
|
| 44336 |
-
"model.layers.92.mlp.experts.139.up_proj.weight": "
|
| 44337 |
-
"model.layers.92.mlp.experts.14.down_proj.weight": "
|
| 44338 |
-
"model.layers.92.mlp.experts.14.gate_proj.weight": "
|
| 44339 |
-
"model.layers.92.mlp.experts.14.up_proj.weight": "
|
| 44340 |
-
"model.layers.92.mlp.experts.140.down_proj.weight": "
|
| 44341 |
-
"model.layers.92.mlp.experts.140.gate_proj.weight": "
|
| 44342 |
-
"model.layers.92.mlp.experts.140.up_proj.weight": "
|
| 44343 |
-
"model.layers.92.mlp.experts.141.down_proj.weight": "
|
| 44344 |
-
"model.layers.92.mlp.experts.141.gate_proj.weight": "
|
| 44345 |
-
"model.layers.92.mlp.experts.141.up_proj.weight": "
|
| 44346 |
-
"model.layers.92.mlp.experts.142.down_proj.weight": "
|
| 44347 |
-
"model.layers.92.mlp.experts.142.gate_proj.weight": "
|
| 44348 |
-
"model.layers.92.mlp.experts.142.up_proj.weight": "
|
| 44349 |
-
"model.layers.92.mlp.experts.143.down_proj.weight": "
|
| 44350 |
-
"model.layers.92.mlp.experts.143.gate_proj.weight": "
|
| 44351 |
-
"model.layers.92.mlp.experts.143.up_proj.weight": "
|
| 44352 |
-
"model.layers.92.mlp.experts.144.down_proj.weight": "
|
| 44353 |
-
"model.layers.92.mlp.experts.144.gate_proj.weight": "
|
| 44354 |
-
"model.layers.92.mlp.experts.144.up_proj.weight": "
|
| 44355 |
-
"model.layers.92.mlp.experts.145.down_proj.weight": "
|
| 44356 |
-
"model.layers.92.mlp.experts.145.gate_proj.weight": "
|
| 44357 |
-
"model.layers.92.mlp.experts.145.up_proj.weight": "
|
| 44358 |
-
"model.layers.92.mlp.experts.146.down_proj.weight": "
|
| 44359 |
-
"model.layers.92.mlp.experts.146.gate_proj.weight": "
|
| 44360 |
-
"model.layers.92.mlp.experts.146.up_proj.weight": "
|
| 44361 |
-
"model.layers.92.mlp.experts.147.down_proj.weight": "
|
| 44362 |
-
"model.layers.92.mlp.experts.147.gate_proj.weight": "
|
| 44363 |
-
"model.layers.92.mlp.experts.147.up_proj.weight": "
|
| 44364 |
-
"model.layers.92.mlp.experts.148.down_proj.weight": "
|
| 44365 |
-
"model.layers.92.mlp.experts.148.gate_proj.weight": "
|
| 44366 |
-
"model.layers.92.mlp.experts.148.up_proj.weight": "
|
| 44367 |
-
"model.layers.92.mlp.experts.149.down_proj.weight": "
|
| 44368 |
-
"model.layers.92.mlp.experts.149.gate_proj.weight": "
|
| 44369 |
-
"model.layers.92.mlp.experts.149.up_proj.weight": "
|
| 44370 |
-
"model.layers.92.mlp.experts.15.down_proj.weight": "
|
| 44371 |
-
"model.layers.92.mlp.experts.15.gate_proj.weight": "
|
| 44372 |
-
"model.layers.92.mlp.experts.15.up_proj.weight": "
|
| 44373 |
-
"model.layers.92.mlp.experts.150.down_proj.weight": "
|
| 44374 |
-
"model.layers.92.mlp.experts.150.gate_proj.weight": "
|
| 44375 |
-
"model.layers.92.mlp.experts.150.up_proj.weight": "
|
| 44376 |
-
"model.layers.92.mlp.experts.151.down_proj.weight": "
|
| 44377 |
-
"model.layers.92.mlp.experts.151.gate_proj.weight": "
|
| 44378 |
-
"model.layers.92.mlp.experts.151.up_proj.weight": "
|
| 44379 |
-
"model.layers.92.mlp.experts.152.down_proj.weight": "
|
| 44380 |
-
"model.layers.92.mlp.experts.152.gate_proj.weight": "
|
| 44381 |
-
"model.layers.92.mlp.experts.152.up_proj.weight": "
|
| 44382 |
-
"model.layers.92.mlp.experts.153.down_proj.weight": "
|
| 44383 |
-
"model.layers.92.mlp.experts.153.gate_proj.weight": "
|
| 44384 |
-
"model.layers.92.mlp.experts.153.up_proj.weight": "
|
| 44385 |
-
"model.layers.92.mlp.experts.154.down_proj.weight": "
|
| 44386 |
-
"model.layers.92.mlp.experts.154.gate_proj.weight": "
|
| 44387 |
-
"model.layers.92.mlp.experts.154.up_proj.weight": "
|
| 44388 |
-
"model.layers.92.mlp.experts.155.down_proj.weight": "
|
| 44389 |
-
"model.layers.92.mlp.experts.155.gate_proj.weight": "
|
| 44390 |
-
"model.layers.92.mlp.experts.155.up_proj.weight": "
|
| 44391 |
-
"model.layers.92.mlp.experts.156.down_proj.weight": "
|
| 44392 |
-
"model.layers.92.mlp.experts.156.gate_proj.weight": "
|
| 44393 |
-
"model.layers.92.mlp.experts.156.up_proj.weight": "
|
| 44394 |
-
"model.layers.92.mlp.experts.157.down_proj.weight": "
|
| 44395 |
-
"model.layers.92.mlp.experts.157.gate_proj.weight": "
|
| 44396 |
-
"model.layers.92.mlp.experts.157.up_proj.weight": "
|
| 44397 |
-
"model.layers.92.mlp.experts.158.down_proj.weight": "
|
| 44398 |
-
"model.layers.92.mlp.experts.158.gate_proj.weight": "
|
| 44399 |
-
"model.layers.92.mlp.experts.158.up_proj.weight": "
|
| 44400 |
-
"model.layers.92.mlp.experts.159.down_proj.weight": "
|
| 44401 |
-
"model.layers.92.mlp.experts.159.gate_proj.weight": "
|
| 44402 |
-
"model.layers.92.mlp.experts.159.up_proj.weight": "
|
| 44403 |
-
"model.layers.92.mlp.experts.16.down_proj.weight": "
|
| 44404 |
-
"model.layers.92.mlp.experts.16.gate_proj.weight": "
|
| 44405 |
-
"model.layers.92.mlp.experts.16.up_proj.weight": "
|
| 44406 |
-
"model.layers.92.mlp.experts.17.down_proj.weight": "
|
| 44407 |
-
"model.layers.92.mlp.experts.17.gate_proj.weight": "
|
| 44408 |
-
"model.layers.92.mlp.experts.17.up_proj.weight": "
|
| 44409 |
-
"model.layers.92.mlp.experts.18.down_proj.weight": "
|
| 44410 |
-
"model.layers.92.mlp.experts.18.gate_proj.weight": "
|
| 44411 |
-
"model.layers.92.mlp.experts.18.up_proj.weight": "
|
| 44412 |
-
"model.layers.92.mlp.experts.19.down_proj.weight": "
|
| 44413 |
-
"model.layers.92.mlp.experts.19.gate_proj.weight": "
|
| 44414 |
-
"model.layers.92.mlp.experts.19.up_proj.weight": "
|
| 44415 |
-
"model.layers.92.mlp.experts.2.down_proj.weight": "
|
| 44416 |
-
"model.layers.92.mlp.experts.2.gate_proj.weight": "
|
| 44417 |
-
"model.layers.92.mlp.experts.2.up_proj.weight": "
|
| 44418 |
-
"model.layers.92.mlp.experts.20.down_proj.weight": "
|
| 44419 |
-
"model.layers.92.mlp.experts.20.gate_proj.weight": "
|
| 44420 |
-
"model.layers.92.mlp.experts.20.up_proj.weight": "
|
| 44421 |
-
"model.layers.92.mlp.experts.21.down_proj.weight": "
|
| 44422 |
-
"model.layers.92.mlp.experts.21.gate_proj.weight": "
|
| 44423 |
-
"model.layers.92.mlp.experts.21.up_proj.weight": "
|
| 44424 |
-
"model.layers.92.mlp.experts.22.down_proj.weight": "
|
| 44425 |
-
"model.layers.92.mlp.experts.22.gate_proj.weight": "
|
| 44426 |
-
"model.layers.92.mlp.experts.22.up_proj.weight": "
|
| 44427 |
-
"model.layers.92.mlp.experts.23.down_proj.weight": "
|
| 44428 |
-
"model.layers.92.mlp.experts.23.gate_proj.weight": "
|
| 44429 |
-
"model.layers.92.mlp.experts.23.up_proj.weight": "
|
| 44430 |
-
"model.layers.92.mlp.experts.24.down_proj.weight": "
|
| 44431 |
-
"model.layers.92.mlp.experts.24.gate_proj.weight": "
|
| 44432 |
-
"model.layers.92.mlp.experts.24.up_proj.weight": "
|
| 44433 |
-
"model.layers.92.mlp.experts.25.down_proj.weight": "
|
| 44434 |
-
"model.layers.92.mlp.experts.25.gate_proj.weight": "
|
| 44435 |
-
"model.layers.92.mlp.experts.25.up_proj.weight": "
|
| 44436 |
-
"model.layers.92.mlp.experts.26.down_proj.weight": "
|
| 44437 |
-
"model.layers.92.mlp.experts.26.gate_proj.weight": "
|
| 44438 |
-
"model.layers.92.mlp.experts.26.up_proj.weight": "
|
| 44439 |
-
"model.layers.92.mlp.experts.27.down_proj.weight": "
|
| 44440 |
-
"model.layers.92.mlp.experts.27.gate_proj.weight": "
|
| 44441 |
-
"model.layers.92.mlp.experts.27.up_proj.weight": "
|
| 44442 |
-
"model.layers.92.mlp.experts.28.down_proj.weight": "
|
| 44443 |
-
"model.layers.92.mlp.experts.28.gate_proj.weight": "
|
| 44444 |
-
"model.layers.92.mlp.experts.28.up_proj.weight": "
|
| 44445 |
-
"model.layers.92.mlp.experts.29.down_proj.weight": "
|
| 44446 |
-
"model.layers.92.mlp.experts.29.gate_proj.weight": "
|
| 44447 |
-
"model.layers.92.mlp.experts.29.up_proj.weight": "
|
| 44448 |
-
"model.layers.92.mlp.experts.3.down_proj.weight": "
|
| 44449 |
-
"model.layers.92.mlp.experts.3.gate_proj.weight": "
|
| 44450 |
-
"model.layers.92.mlp.experts.3.up_proj.weight": "
|
| 44451 |
-
"model.layers.92.mlp.experts.30.down_proj.weight": "
|
| 44452 |
-
"model.layers.92.mlp.experts.30.gate_proj.weight": "
|
| 44453 |
-
"model.layers.92.mlp.experts.30.up_proj.weight": "
|
| 44454 |
-
"model.layers.92.mlp.experts.31.down_proj.weight": "
|
| 44455 |
-
"model.layers.92.mlp.experts.31.gate_proj.weight": "
|
| 44456 |
-
"model.layers.92.mlp.experts.31.up_proj.weight": "
|
| 44457 |
-
"model.layers.92.mlp.experts.32.down_proj.weight": "
|
| 44458 |
-
"model.layers.92.mlp.experts.32.gate_proj.weight": "
|
| 44459 |
-
"model.layers.92.mlp.experts.32.up_proj.weight": "
|
| 44460 |
-
"model.layers.92.mlp.experts.33.down_proj.weight": "
|
| 44461 |
-
"model.layers.92.mlp.experts.33.gate_proj.weight": "
|
| 44462 |
-
"model.layers.92.mlp.experts.33.up_proj.weight": "
|
| 44463 |
-
"model.layers.92.mlp.experts.34.down_proj.weight": "
|
| 44464 |
-
"model.layers.92.mlp.experts.34.gate_proj.weight": "
|
| 44465 |
-
"model.layers.92.mlp.experts.34.up_proj.weight": "
|
| 44466 |
-
"model.layers.92.mlp.experts.35.down_proj.weight": "
|
| 44467 |
-
"model.layers.92.mlp.experts.35.gate_proj.weight": "
|
| 44468 |
-
"model.layers.92.mlp.experts.35.up_proj.weight": "
|
| 44469 |
-
"model.layers.92.mlp.experts.36.down_proj.weight": "
|
| 44470 |
-
"model.layers.92.mlp.experts.36.gate_proj.weight": "
|
| 44471 |
-
"model.layers.92.mlp.experts.36.up_proj.weight": "
|
| 44472 |
-
"model.layers.92.mlp.experts.37.down_proj.weight": "
|
| 44473 |
-
"model.layers.92.mlp.experts.37.gate_proj.weight": "
|
| 44474 |
-
"model.layers.92.mlp.experts.37.up_proj.weight": "
|
| 44475 |
-
"model.layers.92.mlp.experts.38.down_proj.weight": "
|
| 44476 |
-
"model.layers.92.mlp.experts.38.gate_proj.weight": "
|
| 44477 |
-
"model.layers.92.mlp.experts.38.up_proj.weight": "
|
| 44478 |
-
"model.layers.92.mlp.experts.39.down_proj.weight": "
|
| 44479 |
-
"model.layers.92.mlp.experts.39.gate_proj.weight": "
|
| 44480 |
-
"model.layers.92.mlp.experts.39.up_proj.weight": "
|
| 44481 |
-
"model.layers.92.mlp.experts.4.down_proj.weight": "
|
| 44482 |
-
"model.layers.92.mlp.experts.4.gate_proj.weight": "
|
| 44483 |
-
"model.layers.92.mlp.experts.4.up_proj.weight": "
|
| 44484 |
-
"model.layers.92.mlp.experts.40.down_proj.weight": "
|
| 44485 |
-
"model.layers.92.mlp.experts.40.gate_proj.weight": "
|
| 44486 |
-
"model.layers.92.mlp.experts.40.up_proj.weight": "
|
| 44487 |
-
"model.layers.92.mlp.experts.41.down_proj.weight": "
|
| 44488 |
-
"model.layers.92.mlp.experts.41.gate_proj.weight": "
|
| 44489 |
-
"model.layers.92.mlp.experts.41.up_proj.weight": "
|
| 44490 |
-
"model.layers.92.mlp.experts.42.down_proj.weight": "
|
| 44491 |
-
"model.layers.92.mlp.experts.42.gate_proj.weight": "
|
| 44492 |
-
"model.layers.92.mlp.experts.42.up_proj.weight": "
|
| 44493 |
-
"model.layers.92.mlp.experts.43.down_proj.weight": "
|
| 44494 |
-
"model.layers.92.mlp.experts.43.gate_proj.weight": "
|
| 44495 |
-
"model.layers.92.mlp.experts.43.up_proj.weight": "
|
| 44496 |
-
"model.layers.92.mlp.experts.44.down_proj.weight": "
|
| 44497 |
-
"model.layers.92.mlp.experts.44.gate_proj.weight": "
|
| 44498 |
-
"model.layers.92.mlp.experts.44.up_proj.weight": "
|
| 44499 |
-
"model.layers.92.mlp.experts.45.down_proj.weight": "
|
| 44500 |
-
"model.layers.92.mlp.experts.45.gate_proj.weight": "
|
| 44501 |
-
"model.layers.92.mlp.experts.45.up_proj.weight": "
|
| 44502 |
-
"model.layers.92.mlp.experts.46.down_proj.weight": "
|
| 44503 |
-
"model.layers.92.mlp.experts.46.gate_proj.weight": "
|
| 44504 |
-
"model.layers.92.mlp.experts.46.up_proj.weight": "
|
| 44505 |
-
"model.layers.92.mlp.experts.47.down_proj.weight": "
|
| 44506 |
-
"model.layers.92.mlp.experts.47.gate_proj.weight": "
|
| 44507 |
-
"model.layers.92.mlp.experts.47.up_proj.weight": "
|
| 44508 |
-
"model.layers.92.mlp.experts.48.down_proj.weight": "
|
| 44509 |
-
"model.layers.92.mlp.experts.48.gate_proj.weight": "
|
| 44510 |
-
"model.layers.92.mlp.experts.48.up_proj.weight": "
|
| 44511 |
-
"model.layers.92.mlp.experts.49.down_proj.weight": "
|
| 44512 |
-
"model.layers.92.mlp.experts.49.gate_proj.weight": "
|
| 44513 |
-
"model.layers.92.mlp.experts.49.up_proj.weight": "
|
| 44514 |
-
"model.layers.92.mlp.experts.5.down_proj.weight": "
|
| 44515 |
-
"model.layers.92.mlp.experts.5.gate_proj.weight": "
|
| 44516 |
-
"model.layers.92.mlp.experts.5.up_proj.weight": "
|
| 44517 |
-
"model.layers.92.mlp.experts.50.down_proj.weight": "
|
| 44518 |
-
"model.layers.92.mlp.experts.50.gate_proj.weight": "
|
| 44519 |
-
"model.layers.92.mlp.experts.50.up_proj.weight": "
|
| 44520 |
-
"model.layers.92.mlp.experts.51.down_proj.weight": "
|
| 44521 |
-
"model.layers.92.mlp.experts.51.gate_proj.weight": "
|
| 44522 |
-
"model.layers.92.mlp.experts.51.up_proj.weight": "
|
| 44523 |
-
"model.layers.92.mlp.experts.52.down_proj.weight": "
|
| 44524 |
-
"model.layers.92.mlp.experts.52.gate_proj.weight": "
|
| 44525 |
-
"model.layers.92.mlp.experts.52.up_proj.weight": "
|
| 44526 |
-
"model.layers.92.mlp.experts.53.down_proj.weight": "
|
| 44527 |
-
"model.layers.92.mlp.experts.53.gate_proj.weight": "
|
| 44528 |
-
"model.layers.92.mlp.experts.53.up_proj.weight": "
|
| 44529 |
-
"model.layers.92.mlp.experts.54.down_proj.weight": "
|
| 44530 |
-
"model.layers.92.mlp.experts.54.gate_proj.weight": "
|
| 44531 |
-
"model.layers.92.mlp.experts.54.up_proj.weight": "
|
| 44532 |
-
"model.layers.92.mlp.experts.55.down_proj.weight": "
|
| 44533 |
-
"model.layers.92.mlp.experts.55.gate_proj.weight": "
|
| 44534 |
-
"model.layers.92.mlp.experts.55.up_proj.weight": "
|
| 44535 |
-
"model.layers.92.mlp.experts.56.down_proj.weight": "
|
| 44536 |
-
"model.layers.92.mlp.experts.56.gate_proj.weight": "
|
| 44537 |
-
"model.layers.92.mlp.experts.56.up_proj.weight": "
|
| 44538 |
-
"model.layers.92.mlp.experts.57.down_proj.weight": "
|
| 44539 |
-
"model.layers.92.mlp.experts.57.gate_proj.weight": "
|
| 44540 |
-
"model.layers.92.mlp.experts.57.up_proj.weight": "
|
| 44541 |
-
"model.layers.92.mlp.experts.58.down_proj.weight": "
|
| 44542 |
-
"model.layers.92.mlp.experts.58.gate_proj.weight": "
|
| 44543 |
-
"model.layers.92.mlp.experts.58.up_proj.weight": "
|
| 44544 |
-
"model.layers.92.mlp.experts.59.down_proj.weight": "
|
| 44545 |
-
"model.layers.92.mlp.experts.59.gate_proj.weight": "
|
| 44546 |
-
"model.layers.92.mlp.experts.59.up_proj.weight": "
|
| 44547 |
-
"model.layers.92.mlp.experts.6.down_proj.weight": "
|
| 44548 |
-
"model.layers.92.mlp.experts.6.gate_proj.weight": "
|
| 44549 |
-
"model.layers.92.mlp.experts.6.up_proj.weight": "
|
| 44550 |
-
"model.layers.92.mlp.experts.60.down_proj.weight": "
|
| 44551 |
-
"model.layers.92.mlp.experts.60.gate_proj.weight": "
|
| 44552 |
-
"model.layers.92.mlp.experts.60.up_proj.weight": "
|
| 44553 |
-
"model.layers.92.mlp.experts.61.down_proj.weight": "
|
| 44554 |
-
"model.layers.92.mlp.experts.61.gate_proj.weight": "
|
| 44555 |
-
"model.layers.92.mlp.experts.61.up_proj.weight": "
|
| 44556 |
-
"model.layers.92.mlp.experts.62.down_proj.weight": "
|
| 44557 |
-
"model.layers.92.mlp.experts.62.gate_proj.weight": "
|
| 44558 |
-
"model.layers.92.mlp.experts.62.up_proj.weight": "
|
| 44559 |
-
"model.layers.92.mlp.experts.63.down_proj.weight": "
|
| 44560 |
-
"model.layers.92.mlp.experts.63.gate_proj.weight": "
|
| 44561 |
-
"model.layers.92.mlp.experts.63.up_proj.weight": "
|
| 44562 |
-
"model.layers.92.mlp.experts.64.down_proj.weight": "
|
| 44563 |
-
"model.layers.92.mlp.experts.64.gate_proj.weight": "
|
| 44564 |
-
"model.layers.92.mlp.experts.64.up_proj.weight": "
|
| 44565 |
-
"model.layers.92.mlp.experts.65.down_proj.weight": "
|
| 44566 |
-
"model.layers.92.mlp.experts.65.gate_proj.weight": "
|
| 44567 |
-
"model.layers.92.mlp.experts.65.up_proj.weight": "
|
| 44568 |
-
"model.layers.92.mlp.experts.66.down_proj.weight": "
|
| 44569 |
-
"model.layers.92.mlp.experts.66.gate_proj.weight": "
|
| 44570 |
-
"model.layers.92.mlp.experts.66.up_proj.weight": "
|
| 44571 |
-
"model.layers.92.mlp.experts.67.down_proj.weight": "
|
| 44572 |
-
"model.layers.92.mlp.experts.67.gate_proj.weight": "
|
| 44573 |
-
"model.layers.92.mlp.experts.67.up_proj.weight": "
|
| 44574 |
-
"model.layers.92.mlp.experts.68.down_proj.weight": "
|
| 44575 |
-
"model.layers.92.mlp.experts.68.gate_proj.weight": "
|
| 44576 |
-
"model.layers.92.mlp.experts.68.up_proj.weight": "
|
| 44577 |
-
"model.layers.92.mlp.experts.69.down_proj.weight": "
|
| 44578 |
-
"model.layers.92.mlp.experts.69.gate_proj.weight": "
|
| 44579 |
-
"model.layers.92.mlp.experts.69.up_proj.weight": "
|
| 44580 |
-
"model.layers.92.mlp.experts.7.down_proj.weight": "
|
| 44581 |
-
"model.layers.92.mlp.experts.7.gate_proj.weight": "
|
| 44582 |
-
"model.layers.92.mlp.experts.7.up_proj.weight": "
|
| 44583 |
-
"model.layers.92.mlp.experts.70.down_proj.weight": "
|
| 44584 |
-
"model.layers.92.mlp.experts.70.gate_proj.weight": "
|
| 44585 |
-
"model.layers.92.mlp.experts.70.up_proj.weight": "
|
| 44586 |
-
"model.layers.92.mlp.experts.71.down_proj.weight": "
|
| 44587 |
-
"model.layers.92.mlp.experts.71.gate_proj.weight": "
|
| 44588 |
-
"model.layers.92.mlp.experts.71.up_proj.weight": "
|
| 44589 |
-
"model.layers.92.mlp.experts.72.down_proj.weight": "
|
| 44590 |
-
"model.layers.92.mlp.experts.72.gate_proj.weight": "
|
| 44591 |
-
"model.layers.92.mlp.experts.72.up_proj.weight": "
|
| 44592 |
-
"model.layers.92.mlp.experts.73.down_proj.weight": "
|
| 44593 |
-
"model.layers.92.mlp.experts.73.gate_proj.weight": "
|
| 44594 |
-
"model.layers.92.mlp.experts.73.up_proj.weight": "
|
| 44595 |
-
"model.layers.92.mlp.experts.74.down_proj.weight": "
|
| 44596 |
-
"model.layers.92.mlp.experts.74.gate_proj.weight": "
|
| 44597 |
-
"model.layers.92.mlp.experts.74.up_proj.weight": "
|
| 44598 |
-
"model.layers.92.mlp.experts.75.down_proj.weight": "
|
| 44599 |
-
"model.layers.92.mlp.experts.75.gate_proj.weight": "
|
| 44600 |
-
"model.layers.92.mlp.experts.75.up_proj.weight": "
|
| 44601 |
-
"model.layers.92.mlp.experts.76.down_proj.weight": "
|
| 44602 |
-
"model.layers.92.mlp.experts.76.gate_proj.weight": "
|
| 44603 |
-
"model.layers.92.mlp.experts.76.up_proj.weight": "
|
| 44604 |
-
"model.layers.92.mlp.experts.77.down_proj.weight": "
|
| 44605 |
-
"model.layers.92.mlp.experts.77.gate_proj.weight": "
|
| 44606 |
-
"model.layers.92.mlp.experts.77.up_proj.weight": "
|
| 44607 |
-
"model.layers.92.mlp.experts.78.down_proj.weight": "
|
| 44608 |
-
"model.layers.92.mlp.experts.78.gate_proj.weight": "
|
| 44609 |
-
"model.layers.92.mlp.experts.78.up_proj.weight": "
|
| 44610 |
-
"model.layers.92.mlp.experts.79.down_proj.weight": "
|
| 44611 |
-
"model.layers.92.mlp.experts.79.gate_proj.weight": "
|
| 44612 |
-
"model.layers.92.mlp.experts.79.up_proj.weight": "
|
| 44613 |
-
"model.layers.92.mlp.experts.8.down_proj.weight": "
|
| 44614 |
-
"model.layers.92.mlp.experts.8.gate_proj.weight": "
|
| 44615 |
-
"model.layers.92.mlp.experts.8.up_proj.weight": "
|
| 44616 |
-
"model.layers.92.mlp.experts.80.down_proj.weight": "
|
| 44617 |
-
"model.layers.92.mlp.experts.80.gate_proj.weight": "
|
| 44618 |
-
"model.layers.92.mlp.experts.80.up_proj.weight": "
|
| 44619 |
-
"model.layers.92.mlp.experts.81.down_proj.weight": "
|
| 44620 |
-
"model.layers.92.mlp.experts.81.gate_proj.weight": "
|
| 44621 |
-
"model.layers.92.mlp.experts.81.up_proj.weight": "
|
| 44622 |
-
"model.layers.92.mlp.experts.82.down_proj.weight": "
|
| 44623 |
-
"model.layers.92.mlp.experts.82.gate_proj.weight": "
|
| 44624 |
-
"model.layers.92.mlp.experts.82.up_proj.weight": "
|
| 44625 |
-
"model.layers.92.mlp.experts.83.down_proj.weight": "
|
| 44626 |
-
"model.layers.92.mlp.experts.83.gate_proj.weight": "
|
| 44627 |
-
"model.layers.92.mlp.experts.83.up_proj.weight": "
|
| 44628 |
-
"model.layers.92.mlp.experts.84.down_proj.weight": "
|
| 44629 |
-
"model.layers.92.mlp.experts.84.gate_proj.weight": "
|
| 44630 |
-
"model.layers.92.mlp.experts.84.up_proj.weight": "
|
| 44631 |
-
"model.layers.92.mlp.experts.85.down_proj.weight": "
|
| 44632 |
-
"model.layers.92.mlp.experts.85.gate_proj.weight": "
|
| 44633 |
-
"model.layers.92.mlp.experts.85.up_proj.weight": "
|
| 44634 |
-
"model.layers.92.mlp.experts.86.down_proj.weight": "
|
| 44635 |
-
"model.layers.92.mlp.experts.86.gate_proj.weight": "
|
| 44636 |
-
"model.layers.92.mlp.experts.86.up_proj.weight": "
|
| 44637 |
-
"model.layers.92.mlp.experts.87.down_proj.weight": "
|
| 44638 |
-
"model.layers.92.mlp.experts.87.gate_proj.weight": "
|
| 44639 |
-
"model.layers.92.mlp.experts.87.up_proj.weight": "
|
| 44640 |
-
"model.layers.92.mlp.experts.88.down_proj.weight": "
|
| 44641 |
-
"model.layers.92.mlp.experts.88.gate_proj.weight": "
|
| 44642 |
-
"model.layers.92.mlp.experts.88.up_proj.weight": "
|
| 44643 |
-
"model.layers.92.mlp.experts.89.down_proj.weight": "
|
| 44644 |
-
"model.layers.92.mlp.experts.89.gate_proj.weight": "
|
| 44645 |
-
"model.layers.92.mlp.experts.89.up_proj.weight": "
|
| 44646 |
-
"model.layers.92.mlp.experts.9.down_proj.weight": "
|
| 44647 |
-
"model.layers.92.mlp.experts.9.gate_proj.weight": "
|
| 44648 |
-
"model.layers.92.mlp.experts.9.up_proj.weight": "
|
| 44649 |
-
"model.layers.92.mlp.experts.90.down_proj.weight": "
|
| 44650 |
-
"model.layers.92.mlp.experts.90.gate_proj.weight": "
|
| 44651 |
-
"model.layers.92.mlp.experts.90.up_proj.weight": "
|
| 44652 |
-
"model.layers.92.mlp.experts.91.down_proj.weight": "
|
| 44653 |
-
"model.layers.92.mlp.experts.91.gate_proj.weight": "
|
| 44654 |
-
"model.layers.92.mlp.experts.91.up_proj.weight": "
|
| 44655 |
-
"model.layers.92.mlp.experts.92.down_proj.weight": "
|
| 44656 |
-
"model.layers.92.mlp.experts.92.gate_proj.weight": "
|
| 44657 |
-
"model.layers.92.mlp.experts.92.up_proj.weight": "
|
| 44658 |
-
"model.layers.92.mlp.experts.93.down_proj.weight": "
|
| 44659 |
-
"model.layers.92.mlp.experts.93.gate_proj.weight": "
|
| 44660 |
-
"model.layers.92.mlp.experts.93.up_proj.weight": "
|
| 44661 |
-
"model.layers.92.mlp.experts.94.down_proj.weight": "
|
| 44662 |
-
"model.layers.92.mlp.experts.94.gate_proj.weight": "
|
| 44663 |
-
"model.layers.92.mlp.experts.94.up_proj.weight": "
|
| 44664 |
-
"model.layers.92.mlp.experts.95.down_proj.weight": "
|
| 44665 |
-
"model.layers.92.mlp.experts.95.gate_proj.weight": "
|
| 44666 |
-
"model.layers.92.mlp.experts.95.up_proj.weight": "
|
| 44667 |
-
"model.layers.92.mlp.experts.96.down_proj.weight": "
|
| 44668 |
-
"model.layers.92.mlp.experts.96.gate_proj.weight": "
|
| 44669 |
-
"model.layers.92.mlp.experts.96.up_proj.weight": "
|
| 44670 |
-
"model.layers.92.mlp.experts.97.down_proj.weight": "
|
| 44671 |
-
"model.layers.92.mlp.experts.97.gate_proj.weight": "
|
| 44672 |
-
"model.layers.92.mlp.experts.97.up_proj.weight": "
|
| 44673 |
-
"model.layers.92.mlp.experts.98.down_proj.weight": "
|
| 44674 |
-
"model.layers.92.mlp.experts.98.gate_proj.weight": "
|
| 44675 |
-
"model.layers.92.mlp.experts.98.up_proj.weight": "
|
| 44676 |
-
"model.layers.92.mlp.experts.99.down_proj.weight": "
|
| 44677 |
-
"model.layers.92.mlp.experts.99.gate_proj.weight": "
|
| 44678 |
-
"model.layers.92.mlp.experts.99.up_proj.weight": "
|
| 44679 |
-
"model.layers.92.mlp.gate.e_score_correction_bias": "
|
| 44680 |
-
"model.layers.92.mlp.gate.weight": "
|
| 44681 |
-
"model.layers.92.mlp.shared_experts.down_proj.weight": "
|
| 44682 |
-
"model.layers.92.mlp.shared_experts.gate_proj.weight": "
|
| 44683 |
-
"model.layers.92.mlp.shared_experts.up_proj.weight": "
|
| 44684 |
-
"model.layers.92.post_attention_layernorm.weight": "
|
| 44685 |
-
"model.layers.92.self_attn.k_norm.weight": "
|
| 44686 |
-
"model.layers.92.self_attn.k_proj.bias": "
|
| 44687 |
-
"model.layers.92.self_attn.k_proj.weight": "
|
| 44688 |
-
"model.layers.92.self_attn.o_proj.weight": "
|
| 44689 |
-
"model.layers.92.self_attn.q_norm.weight": "
|
| 44690 |
-
"model.layers.92.self_attn.q_proj.bias": "
|
| 44691 |
-
"model.layers.92.self_attn.q_proj.weight": "
|
| 44692 |
-
"model.layers.92.self_attn.v_proj.bias": "
|
| 44693 |
-
"model.layers.92.self_attn.v_proj.weight": "
|
| 44694 |
-
"model.layers.92.shared_head.norm.weight": "
|
| 44695 |
}
|
| 44696 |
}
|
|
|
|
| 44192 |
"model.layers.91.self_attn.v_proj.bias": "model-00092-of-00092.safetensors",
|
| 44193 |
"model.layers.91.self_attn.v_proj.weight": "model-00092-of-00092.safetensors",
|
| 44194 |
"model.norm.weight": "model-00092-of-00092.safetensors",
|
| 44195 |
+
"model.layers.92.eh_proj.weight": "mtp.safetensors",
|
| 44196 |
+
"model.layers.92.enorm.weight": "mtp.safetensors",
|
| 44197 |
+
"model.layers.92.hnorm.weight": "mtp.safetensors",
|
| 44198 |
+
"model.layers.92.input_layernorm.weight": "mtp.safetensors",
|
| 44199 |
+
"model.layers.92.mlp.experts.0.down_proj.weight": "mtp.safetensors",
|
| 44200 |
+
"model.layers.92.mlp.experts.0.gate_proj.weight": "mtp.safetensors",
|
| 44201 |
+
"model.layers.92.mlp.experts.0.up_proj.weight": "mtp.safetensors",
|
| 44202 |
+
"model.layers.92.mlp.experts.1.down_proj.weight": "mtp.safetensors",
|
| 44203 |
+
"model.layers.92.mlp.experts.1.gate_proj.weight": "mtp.safetensors",
|
| 44204 |
+
"model.layers.92.mlp.experts.1.up_proj.weight": "mtp.safetensors",
|
| 44205 |
+
"model.layers.92.mlp.experts.10.down_proj.weight": "mtp.safetensors",
|
| 44206 |
+
"model.layers.92.mlp.experts.10.gate_proj.weight": "mtp.safetensors",
|
| 44207 |
+
"model.layers.92.mlp.experts.10.up_proj.weight": "mtp.safetensors",
|
| 44208 |
+
"model.layers.92.mlp.experts.100.down_proj.weight": "mtp.safetensors",
|
| 44209 |
+
"model.layers.92.mlp.experts.100.gate_proj.weight": "mtp.safetensors",
|
| 44210 |
+
"model.layers.92.mlp.experts.100.up_proj.weight": "mtp.safetensors",
|
| 44211 |
+
"model.layers.92.mlp.experts.101.down_proj.weight": "mtp.safetensors",
|
| 44212 |
+
"model.layers.92.mlp.experts.101.gate_proj.weight": "mtp.safetensors",
|
| 44213 |
+
"model.layers.92.mlp.experts.101.up_proj.weight": "mtp.safetensors",
|
| 44214 |
+
"model.layers.92.mlp.experts.102.down_proj.weight": "mtp.safetensors",
|
| 44215 |
+
"model.layers.92.mlp.experts.102.gate_proj.weight": "mtp.safetensors",
|
| 44216 |
+
"model.layers.92.mlp.experts.102.up_proj.weight": "mtp.safetensors",
|
| 44217 |
+
"model.layers.92.mlp.experts.103.down_proj.weight": "mtp.safetensors",
|
| 44218 |
+
"model.layers.92.mlp.experts.103.gate_proj.weight": "mtp.safetensors",
|
| 44219 |
+
"model.layers.92.mlp.experts.103.up_proj.weight": "mtp.safetensors",
|
| 44220 |
+
"model.layers.92.mlp.experts.104.down_proj.weight": "mtp.safetensors",
|
| 44221 |
+
"model.layers.92.mlp.experts.104.gate_proj.weight": "mtp.safetensors",
|
| 44222 |
+
"model.layers.92.mlp.experts.104.up_proj.weight": "mtp.safetensors",
|
| 44223 |
+
"model.layers.92.mlp.experts.105.down_proj.weight": "mtp.safetensors",
|
| 44224 |
+
"model.layers.92.mlp.experts.105.gate_proj.weight": "mtp.safetensors",
|
| 44225 |
+
"model.layers.92.mlp.experts.105.up_proj.weight": "mtp.safetensors",
|
| 44226 |
+
"model.layers.92.mlp.experts.106.down_proj.weight": "mtp.safetensors",
|
| 44227 |
+
"model.layers.92.mlp.experts.106.gate_proj.weight": "mtp.safetensors",
|
| 44228 |
+
"model.layers.92.mlp.experts.106.up_proj.weight": "mtp.safetensors",
|
| 44229 |
+
"model.layers.92.mlp.experts.107.down_proj.weight": "mtp.safetensors",
|
| 44230 |
+
"model.layers.92.mlp.experts.107.gate_proj.weight": "mtp.safetensors",
|
| 44231 |
+
"model.layers.92.mlp.experts.107.up_proj.weight": "mtp.safetensors",
|
| 44232 |
+
"model.layers.92.mlp.experts.108.down_proj.weight": "mtp.safetensors",
|
| 44233 |
+
"model.layers.92.mlp.experts.108.gate_proj.weight": "mtp.safetensors",
|
| 44234 |
+
"model.layers.92.mlp.experts.108.up_proj.weight": "mtp.safetensors",
|
| 44235 |
+
"model.layers.92.mlp.experts.109.down_proj.weight": "mtp.safetensors",
|
| 44236 |
+
"model.layers.92.mlp.experts.109.gate_proj.weight": "mtp.safetensors",
|
| 44237 |
+
"model.layers.92.mlp.experts.109.up_proj.weight": "mtp.safetensors",
|
| 44238 |
+
"model.layers.92.mlp.experts.11.down_proj.weight": "mtp.safetensors",
|
| 44239 |
+
"model.layers.92.mlp.experts.11.gate_proj.weight": "mtp.safetensors",
|
| 44240 |
+
"model.layers.92.mlp.experts.11.up_proj.weight": "mtp.safetensors",
|
| 44241 |
+
"model.layers.92.mlp.experts.110.down_proj.weight": "mtp.safetensors",
|
| 44242 |
+
"model.layers.92.mlp.experts.110.gate_proj.weight": "mtp.safetensors",
|
| 44243 |
+
"model.layers.92.mlp.experts.110.up_proj.weight": "mtp.safetensors",
|
| 44244 |
+
"model.layers.92.mlp.experts.111.down_proj.weight": "mtp.safetensors",
|
| 44245 |
+
"model.layers.92.mlp.experts.111.gate_proj.weight": "mtp.safetensors",
|
| 44246 |
+
"model.layers.92.mlp.experts.111.up_proj.weight": "mtp.safetensors",
|
| 44247 |
+
"model.layers.92.mlp.experts.112.down_proj.weight": "mtp.safetensors",
|
| 44248 |
+
"model.layers.92.mlp.experts.112.gate_proj.weight": "mtp.safetensors",
|
| 44249 |
+
"model.layers.92.mlp.experts.112.up_proj.weight": "mtp.safetensors",
|
| 44250 |
+
"model.layers.92.mlp.experts.113.down_proj.weight": "mtp.safetensors",
|
| 44251 |
+
"model.layers.92.mlp.experts.113.gate_proj.weight": "mtp.safetensors",
|
| 44252 |
+
"model.layers.92.mlp.experts.113.up_proj.weight": "mtp.safetensors",
|
| 44253 |
+
"model.layers.92.mlp.experts.114.down_proj.weight": "mtp.safetensors",
|
| 44254 |
+
"model.layers.92.mlp.experts.114.gate_proj.weight": "mtp.safetensors",
|
| 44255 |
+
"model.layers.92.mlp.experts.114.up_proj.weight": "mtp.safetensors",
|
| 44256 |
+
"model.layers.92.mlp.experts.115.down_proj.weight": "mtp.safetensors",
|
| 44257 |
+
"model.layers.92.mlp.experts.115.gate_proj.weight": "mtp.safetensors",
|
| 44258 |
+
"model.layers.92.mlp.experts.115.up_proj.weight": "mtp.safetensors",
|
| 44259 |
+
"model.layers.92.mlp.experts.116.down_proj.weight": "mtp.safetensors",
|
| 44260 |
+
"model.layers.92.mlp.experts.116.gate_proj.weight": "mtp.safetensors",
|
| 44261 |
+
"model.layers.92.mlp.experts.116.up_proj.weight": "mtp.safetensors",
|
| 44262 |
+
"model.layers.92.mlp.experts.117.down_proj.weight": "mtp.safetensors",
|
| 44263 |
+
"model.layers.92.mlp.experts.117.gate_proj.weight": "mtp.safetensors",
|
| 44264 |
+
"model.layers.92.mlp.experts.117.up_proj.weight": "mtp.safetensors",
|
| 44265 |
+
"model.layers.92.mlp.experts.118.down_proj.weight": "mtp.safetensors",
|
| 44266 |
+
"model.layers.92.mlp.experts.118.gate_proj.weight": "mtp.safetensors",
|
| 44267 |
+
"model.layers.92.mlp.experts.118.up_proj.weight": "mtp.safetensors",
|
| 44268 |
+
"model.layers.92.mlp.experts.119.down_proj.weight": "mtp.safetensors",
|
| 44269 |
+
"model.layers.92.mlp.experts.119.gate_proj.weight": "mtp.safetensors",
|
| 44270 |
+
"model.layers.92.mlp.experts.119.up_proj.weight": "mtp.safetensors",
|
| 44271 |
+
"model.layers.92.mlp.experts.12.down_proj.weight": "mtp.safetensors",
|
| 44272 |
+
"model.layers.92.mlp.experts.12.gate_proj.weight": "mtp.safetensors",
|
| 44273 |
+
"model.layers.92.mlp.experts.12.up_proj.weight": "mtp.safetensors",
|
| 44274 |
+
"model.layers.92.mlp.experts.120.down_proj.weight": "mtp.safetensors",
|
| 44275 |
+
"model.layers.92.mlp.experts.120.gate_proj.weight": "mtp.safetensors",
|
| 44276 |
+
"model.layers.92.mlp.experts.120.up_proj.weight": "mtp.safetensors",
|
| 44277 |
+
"model.layers.92.mlp.experts.121.down_proj.weight": "mtp.safetensors",
|
| 44278 |
+
"model.layers.92.mlp.experts.121.gate_proj.weight": "mtp.safetensors",
|
| 44279 |
+
"model.layers.92.mlp.experts.121.up_proj.weight": "mtp.safetensors",
|
| 44280 |
+
"model.layers.92.mlp.experts.122.down_proj.weight": "mtp.safetensors",
|
| 44281 |
+
"model.layers.92.mlp.experts.122.gate_proj.weight": "mtp.safetensors",
|
| 44282 |
+
"model.layers.92.mlp.experts.122.up_proj.weight": "mtp.safetensors",
|
| 44283 |
+
"model.layers.92.mlp.experts.123.down_proj.weight": "mtp.safetensors",
|
| 44284 |
+
"model.layers.92.mlp.experts.123.gate_proj.weight": "mtp.safetensors",
|
| 44285 |
+
"model.layers.92.mlp.experts.123.up_proj.weight": "mtp.safetensors",
|
| 44286 |
+
"model.layers.92.mlp.experts.124.down_proj.weight": "mtp.safetensors",
|
| 44287 |
+
"model.layers.92.mlp.experts.124.gate_proj.weight": "mtp.safetensors",
|
| 44288 |
+
"model.layers.92.mlp.experts.124.up_proj.weight": "mtp.safetensors",
|
| 44289 |
+
"model.layers.92.mlp.experts.125.down_proj.weight": "mtp.safetensors",
|
| 44290 |
+
"model.layers.92.mlp.experts.125.gate_proj.weight": "mtp.safetensors",
|
| 44291 |
+
"model.layers.92.mlp.experts.125.up_proj.weight": "mtp.safetensors",
|
| 44292 |
+
"model.layers.92.mlp.experts.126.down_proj.weight": "mtp.safetensors",
|
| 44293 |
+
"model.layers.92.mlp.experts.126.gate_proj.weight": "mtp.safetensors",
|
| 44294 |
+
"model.layers.92.mlp.experts.126.up_proj.weight": "mtp.safetensors",
|
| 44295 |
+
"model.layers.92.mlp.experts.127.down_proj.weight": "mtp.safetensors",
|
| 44296 |
+
"model.layers.92.mlp.experts.127.gate_proj.weight": "mtp.safetensors",
|
| 44297 |
+
"model.layers.92.mlp.experts.127.up_proj.weight": "mtp.safetensors",
|
| 44298 |
+
"model.layers.92.mlp.experts.128.down_proj.weight": "mtp.safetensors",
|
| 44299 |
+
"model.layers.92.mlp.experts.128.gate_proj.weight": "mtp.safetensors",
|
| 44300 |
+
"model.layers.92.mlp.experts.128.up_proj.weight": "mtp.safetensors",
|
| 44301 |
+
"model.layers.92.mlp.experts.129.down_proj.weight": "mtp.safetensors",
|
| 44302 |
+
"model.layers.92.mlp.experts.129.gate_proj.weight": "mtp.safetensors",
|
| 44303 |
+
"model.layers.92.mlp.experts.129.up_proj.weight": "mtp.safetensors",
|
| 44304 |
+
"model.layers.92.mlp.experts.13.down_proj.weight": "mtp.safetensors",
|
| 44305 |
+
"model.layers.92.mlp.experts.13.gate_proj.weight": "mtp.safetensors",
|
| 44306 |
+
"model.layers.92.mlp.experts.13.up_proj.weight": "mtp.safetensors",
|
| 44307 |
+
"model.layers.92.mlp.experts.130.down_proj.weight": "mtp.safetensors",
|
| 44308 |
+
"model.layers.92.mlp.experts.130.gate_proj.weight": "mtp.safetensors",
|
| 44309 |
+
"model.layers.92.mlp.experts.130.up_proj.weight": "mtp.safetensors",
|
| 44310 |
+
"model.layers.92.mlp.experts.131.down_proj.weight": "mtp.safetensors",
|
| 44311 |
+
"model.layers.92.mlp.experts.131.gate_proj.weight": "mtp.safetensors",
|
| 44312 |
+
"model.layers.92.mlp.experts.131.up_proj.weight": "mtp.safetensors",
|
| 44313 |
+
"model.layers.92.mlp.experts.132.down_proj.weight": "mtp.safetensors",
|
| 44314 |
+
"model.layers.92.mlp.experts.132.gate_proj.weight": "mtp.safetensors",
|
| 44315 |
+
"model.layers.92.mlp.experts.132.up_proj.weight": "mtp.safetensors",
|
| 44316 |
+
"model.layers.92.mlp.experts.133.down_proj.weight": "mtp.safetensors",
|
| 44317 |
+
"model.layers.92.mlp.experts.133.gate_proj.weight": "mtp.safetensors",
|
| 44318 |
+
"model.layers.92.mlp.experts.133.up_proj.weight": "mtp.safetensors",
|
| 44319 |
+
"model.layers.92.mlp.experts.134.down_proj.weight": "mtp.safetensors",
|
| 44320 |
+
"model.layers.92.mlp.experts.134.gate_proj.weight": "mtp.safetensors",
|
| 44321 |
+
"model.layers.92.mlp.experts.134.up_proj.weight": "mtp.safetensors",
|
| 44322 |
+
"model.layers.92.mlp.experts.135.down_proj.weight": "mtp.safetensors",
|
| 44323 |
+
"model.layers.92.mlp.experts.135.gate_proj.weight": "mtp.safetensors",
|
| 44324 |
+
"model.layers.92.mlp.experts.135.up_proj.weight": "mtp.safetensors",
|
| 44325 |
+
"model.layers.92.mlp.experts.136.down_proj.weight": "mtp.safetensors",
|
| 44326 |
+
"model.layers.92.mlp.experts.136.gate_proj.weight": "mtp.safetensors",
|
| 44327 |
+
"model.layers.92.mlp.experts.136.up_proj.weight": "mtp.safetensors",
|
| 44328 |
+
"model.layers.92.mlp.experts.137.down_proj.weight": "mtp.safetensors",
|
| 44329 |
+
"model.layers.92.mlp.experts.137.gate_proj.weight": "mtp.safetensors",
|
| 44330 |
+
"model.layers.92.mlp.experts.137.up_proj.weight": "mtp.safetensors",
|
| 44331 |
+
"model.layers.92.mlp.experts.138.down_proj.weight": "mtp.safetensors",
|
| 44332 |
+
"model.layers.92.mlp.experts.138.gate_proj.weight": "mtp.safetensors",
|
| 44333 |
+
"model.layers.92.mlp.experts.138.up_proj.weight": "mtp.safetensors",
|
| 44334 |
+
"model.layers.92.mlp.experts.139.down_proj.weight": "mtp.safetensors",
|
| 44335 |
+
"model.layers.92.mlp.experts.139.gate_proj.weight": "mtp.safetensors",
|
| 44336 |
+
"model.layers.92.mlp.experts.139.up_proj.weight": "mtp.safetensors",
|
| 44337 |
+
"model.layers.92.mlp.experts.14.down_proj.weight": "mtp.safetensors",
|
| 44338 |
+
"model.layers.92.mlp.experts.14.gate_proj.weight": "mtp.safetensors",
|
| 44339 |
+
"model.layers.92.mlp.experts.14.up_proj.weight": "mtp.safetensors",
|
| 44340 |
+
"model.layers.92.mlp.experts.140.down_proj.weight": "mtp.safetensors",
|
| 44341 |
+
"model.layers.92.mlp.experts.140.gate_proj.weight": "mtp.safetensors",
|
| 44342 |
+
"model.layers.92.mlp.experts.140.up_proj.weight": "mtp.safetensors",
|
| 44343 |
+
"model.layers.92.mlp.experts.141.down_proj.weight": "mtp.safetensors",
|
| 44344 |
+
"model.layers.92.mlp.experts.141.gate_proj.weight": "mtp.safetensors",
|
| 44345 |
+
"model.layers.92.mlp.experts.141.up_proj.weight": "mtp.safetensors",
|
| 44346 |
+
"model.layers.92.mlp.experts.142.down_proj.weight": "mtp.safetensors",
|
| 44347 |
+
"model.layers.92.mlp.experts.142.gate_proj.weight": "mtp.safetensors",
|
| 44348 |
+
"model.layers.92.mlp.experts.142.up_proj.weight": "mtp.safetensors",
|
| 44349 |
+
"model.layers.92.mlp.experts.143.down_proj.weight": "mtp.safetensors",
|
| 44350 |
+
"model.layers.92.mlp.experts.143.gate_proj.weight": "mtp.safetensors",
|
| 44351 |
+
"model.layers.92.mlp.experts.143.up_proj.weight": "mtp.safetensors",
|
| 44352 |
+
"model.layers.92.mlp.experts.144.down_proj.weight": "mtp.safetensors",
|
| 44353 |
+
"model.layers.92.mlp.experts.144.gate_proj.weight": "mtp.safetensors",
|
| 44354 |
+
"model.layers.92.mlp.experts.144.up_proj.weight": "mtp.safetensors",
|
| 44355 |
+
"model.layers.92.mlp.experts.145.down_proj.weight": "mtp.safetensors",
|
| 44356 |
+
"model.layers.92.mlp.experts.145.gate_proj.weight": "mtp.safetensors",
|
| 44357 |
+
"model.layers.92.mlp.experts.145.up_proj.weight": "mtp.safetensors",
|
| 44358 |
+
"model.layers.92.mlp.experts.146.down_proj.weight": "mtp.safetensors",
|
| 44359 |
+
"model.layers.92.mlp.experts.146.gate_proj.weight": "mtp.safetensors",
|
| 44360 |
+
"model.layers.92.mlp.experts.146.up_proj.weight": "mtp.safetensors",
|
| 44361 |
+
"model.layers.92.mlp.experts.147.down_proj.weight": "mtp.safetensors",
|
| 44362 |
+
"model.layers.92.mlp.experts.147.gate_proj.weight": "mtp.safetensors",
|
| 44363 |
+
"model.layers.92.mlp.experts.147.up_proj.weight": "mtp.safetensors",
|
| 44364 |
+
"model.layers.92.mlp.experts.148.down_proj.weight": "mtp.safetensors",
|
| 44365 |
+
"model.layers.92.mlp.experts.148.gate_proj.weight": "mtp.safetensors",
|
| 44366 |
+
"model.layers.92.mlp.experts.148.up_proj.weight": "mtp.safetensors",
|
| 44367 |
+
"model.layers.92.mlp.experts.149.down_proj.weight": "mtp.safetensors",
|
| 44368 |
+
"model.layers.92.mlp.experts.149.gate_proj.weight": "mtp.safetensors",
|
| 44369 |
+
"model.layers.92.mlp.experts.149.up_proj.weight": "mtp.safetensors",
|
| 44370 |
+
"model.layers.92.mlp.experts.15.down_proj.weight": "mtp.safetensors",
|
| 44371 |
+
"model.layers.92.mlp.experts.15.gate_proj.weight": "mtp.safetensors",
|
| 44372 |
+
"model.layers.92.mlp.experts.15.up_proj.weight": "mtp.safetensors",
|
| 44373 |
+
"model.layers.92.mlp.experts.150.down_proj.weight": "mtp.safetensors",
|
| 44374 |
+
"model.layers.92.mlp.experts.150.gate_proj.weight": "mtp.safetensors",
|
| 44375 |
+
"model.layers.92.mlp.experts.150.up_proj.weight": "mtp.safetensors",
|
| 44376 |
+
"model.layers.92.mlp.experts.151.down_proj.weight": "mtp.safetensors",
|
| 44377 |
+
"model.layers.92.mlp.experts.151.gate_proj.weight": "mtp.safetensors",
|
| 44378 |
+
"model.layers.92.mlp.experts.151.up_proj.weight": "mtp.safetensors",
|
| 44379 |
+
"model.layers.92.mlp.experts.152.down_proj.weight": "mtp.safetensors",
|
| 44380 |
+
"model.layers.92.mlp.experts.152.gate_proj.weight": "mtp.safetensors",
|
| 44381 |
+
"model.layers.92.mlp.experts.152.up_proj.weight": "mtp.safetensors",
|
| 44382 |
+
"model.layers.92.mlp.experts.153.down_proj.weight": "mtp.safetensors",
|
| 44383 |
+
"model.layers.92.mlp.experts.153.gate_proj.weight": "mtp.safetensors",
|
| 44384 |
+
"model.layers.92.mlp.experts.153.up_proj.weight": "mtp.safetensors",
|
| 44385 |
+
"model.layers.92.mlp.experts.154.down_proj.weight": "mtp.safetensors",
|
| 44386 |
+
"model.layers.92.mlp.experts.154.gate_proj.weight": "mtp.safetensors",
|
| 44387 |
+
"model.layers.92.mlp.experts.154.up_proj.weight": "mtp.safetensors",
|
| 44388 |
+
"model.layers.92.mlp.experts.155.down_proj.weight": "mtp.safetensors",
|
| 44389 |
+
"model.layers.92.mlp.experts.155.gate_proj.weight": "mtp.safetensors",
|
| 44390 |
+
"model.layers.92.mlp.experts.155.up_proj.weight": "mtp.safetensors",
|
| 44391 |
+
"model.layers.92.mlp.experts.156.down_proj.weight": "mtp.safetensors",
|
| 44392 |
+
"model.layers.92.mlp.experts.156.gate_proj.weight": "mtp.safetensors",
|
| 44393 |
+
"model.layers.92.mlp.experts.156.up_proj.weight": "mtp.safetensors",
|
| 44394 |
+
"model.layers.92.mlp.experts.157.down_proj.weight": "mtp.safetensors",
|
| 44395 |
+
"model.layers.92.mlp.experts.157.gate_proj.weight": "mtp.safetensors",
|
| 44396 |
+
"model.layers.92.mlp.experts.157.up_proj.weight": "mtp.safetensors",
|
| 44397 |
+
"model.layers.92.mlp.experts.158.down_proj.weight": "mtp.safetensors",
|
| 44398 |
+
"model.layers.92.mlp.experts.158.gate_proj.weight": "mtp.safetensors",
|
| 44399 |
+
"model.layers.92.mlp.experts.158.up_proj.weight": "mtp.safetensors",
|
| 44400 |
+
"model.layers.92.mlp.experts.159.down_proj.weight": "mtp.safetensors",
|
| 44401 |
+
"model.layers.92.mlp.experts.159.gate_proj.weight": "mtp.safetensors",
|
| 44402 |
+
"model.layers.92.mlp.experts.159.up_proj.weight": "mtp.safetensors",
|
| 44403 |
+
"model.layers.92.mlp.experts.16.down_proj.weight": "mtp.safetensors",
|
| 44404 |
+
"model.layers.92.mlp.experts.16.gate_proj.weight": "mtp.safetensors",
|
| 44405 |
+
"model.layers.92.mlp.experts.16.up_proj.weight": "mtp.safetensors",
|
| 44406 |
+
"model.layers.92.mlp.experts.17.down_proj.weight": "mtp.safetensors",
|
| 44407 |
+
"model.layers.92.mlp.experts.17.gate_proj.weight": "mtp.safetensors",
|
| 44408 |
+
"model.layers.92.mlp.experts.17.up_proj.weight": "mtp.safetensors",
|
| 44409 |
+
"model.layers.92.mlp.experts.18.down_proj.weight": "mtp.safetensors",
|
| 44410 |
+
"model.layers.92.mlp.experts.18.gate_proj.weight": "mtp.safetensors",
|
| 44411 |
+
"model.layers.92.mlp.experts.18.up_proj.weight": "mtp.safetensors",
|
| 44412 |
+
"model.layers.92.mlp.experts.19.down_proj.weight": "mtp.safetensors",
|
| 44413 |
+
"model.layers.92.mlp.experts.19.gate_proj.weight": "mtp.safetensors",
|
| 44414 |
+
"model.layers.92.mlp.experts.19.up_proj.weight": "mtp.safetensors",
|
| 44415 |
+
"model.layers.92.mlp.experts.2.down_proj.weight": "mtp.safetensors",
|
| 44416 |
+
"model.layers.92.mlp.experts.2.gate_proj.weight": "mtp.safetensors",
|
| 44417 |
+
"model.layers.92.mlp.experts.2.up_proj.weight": "mtp.safetensors",
|
| 44418 |
+
"model.layers.92.mlp.experts.20.down_proj.weight": "mtp.safetensors",
|
| 44419 |
+
"model.layers.92.mlp.experts.20.gate_proj.weight": "mtp.safetensors",
|
| 44420 |
+
"model.layers.92.mlp.experts.20.up_proj.weight": "mtp.safetensors",
|
| 44421 |
+
"model.layers.92.mlp.experts.21.down_proj.weight": "mtp.safetensors",
|
| 44422 |
+
"model.layers.92.mlp.experts.21.gate_proj.weight": "mtp.safetensors",
|
| 44423 |
+
"model.layers.92.mlp.experts.21.up_proj.weight": "mtp.safetensors",
|
| 44424 |
+
"model.layers.92.mlp.experts.22.down_proj.weight": "mtp.safetensors",
|
| 44425 |
+
"model.layers.92.mlp.experts.22.gate_proj.weight": "mtp.safetensors",
|
| 44426 |
+
"model.layers.92.mlp.experts.22.up_proj.weight": "mtp.safetensors",
|
| 44427 |
+
"model.layers.92.mlp.experts.23.down_proj.weight": "mtp.safetensors",
|
| 44428 |
+
"model.layers.92.mlp.experts.23.gate_proj.weight": "mtp.safetensors",
|
| 44429 |
+
"model.layers.92.mlp.experts.23.up_proj.weight": "mtp.safetensors",
|
| 44430 |
+
"model.layers.92.mlp.experts.24.down_proj.weight": "mtp.safetensors",
|
| 44431 |
+
"model.layers.92.mlp.experts.24.gate_proj.weight": "mtp.safetensors",
|
| 44432 |
+
"model.layers.92.mlp.experts.24.up_proj.weight": "mtp.safetensors",
|
| 44433 |
+
"model.layers.92.mlp.experts.25.down_proj.weight": "mtp.safetensors",
|
| 44434 |
+
"model.layers.92.mlp.experts.25.gate_proj.weight": "mtp.safetensors",
|
| 44435 |
+
"model.layers.92.mlp.experts.25.up_proj.weight": "mtp.safetensors",
|
| 44436 |
+
"model.layers.92.mlp.experts.26.down_proj.weight": "mtp.safetensors",
|
| 44437 |
+
"model.layers.92.mlp.experts.26.gate_proj.weight": "mtp.safetensors",
|
| 44438 |
+
"model.layers.92.mlp.experts.26.up_proj.weight": "mtp.safetensors",
|
| 44439 |
+
"model.layers.92.mlp.experts.27.down_proj.weight": "mtp.safetensors",
|
| 44440 |
+
"model.layers.92.mlp.experts.27.gate_proj.weight": "mtp.safetensors",
|
| 44441 |
+
"model.layers.92.mlp.experts.27.up_proj.weight": "mtp.safetensors",
|
| 44442 |
+
"model.layers.92.mlp.experts.28.down_proj.weight": "mtp.safetensors",
|
| 44443 |
+
"model.layers.92.mlp.experts.28.gate_proj.weight": "mtp.safetensors",
|
| 44444 |
+
"model.layers.92.mlp.experts.28.up_proj.weight": "mtp.safetensors",
|
| 44445 |
+
"model.layers.92.mlp.experts.29.down_proj.weight": "mtp.safetensors",
|
| 44446 |
+
"model.layers.92.mlp.experts.29.gate_proj.weight": "mtp.safetensors",
|
| 44447 |
+
"model.layers.92.mlp.experts.29.up_proj.weight": "mtp.safetensors",
|
| 44448 |
+
"model.layers.92.mlp.experts.3.down_proj.weight": "mtp.safetensors",
|
| 44449 |
+
"model.layers.92.mlp.experts.3.gate_proj.weight": "mtp.safetensors",
|
| 44450 |
+
"model.layers.92.mlp.experts.3.up_proj.weight": "mtp.safetensors",
|
| 44451 |
+
"model.layers.92.mlp.experts.30.down_proj.weight": "mtp.safetensors",
|
| 44452 |
+
"model.layers.92.mlp.experts.30.gate_proj.weight": "mtp.safetensors",
|
| 44453 |
+
"model.layers.92.mlp.experts.30.up_proj.weight": "mtp.safetensors",
|
| 44454 |
+
"model.layers.92.mlp.experts.31.down_proj.weight": "mtp.safetensors",
|
| 44455 |
+
"model.layers.92.mlp.experts.31.gate_proj.weight": "mtp.safetensors",
|
| 44456 |
+
"model.layers.92.mlp.experts.31.up_proj.weight": "mtp.safetensors",
|
| 44457 |
+
"model.layers.92.mlp.experts.32.down_proj.weight": "mtp.safetensors",
|
| 44458 |
+
"model.layers.92.mlp.experts.32.gate_proj.weight": "mtp.safetensors",
|
| 44459 |
+
"model.layers.92.mlp.experts.32.up_proj.weight": "mtp.safetensors",
|
| 44460 |
+
"model.layers.92.mlp.experts.33.down_proj.weight": "mtp.safetensors",
|
| 44461 |
+
"model.layers.92.mlp.experts.33.gate_proj.weight": "mtp.safetensors",
|
| 44462 |
+
"model.layers.92.mlp.experts.33.up_proj.weight": "mtp.safetensors",
|
| 44463 |
+
"model.layers.92.mlp.experts.34.down_proj.weight": "mtp.safetensors",
|
| 44464 |
+
"model.layers.92.mlp.experts.34.gate_proj.weight": "mtp.safetensors",
|
| 44465 |
+
"model.layers.92.mlp.experts.34.up_proj.weight": "mtp.safetensors",
|
| 44466 |
+
"model.layers.92.mlp.experts.35.down_proj.weight": "mtp.safetensors",
|
| 44467 |
+
"model.layers.92.mlp.experts.35.gate_proj.weight": "mtp.safetensors",
|
| 44468 |
+
"model.layers.92.mlp.experts.35.up_proj.weight": "mtp.safetensors",
|
| 44469 |
+
"model.layers.92.mlp.experts.36.down_proj.weight": "mtp.safetensors",
|
| 44470 |
+
"model.layers.92.mlp.experts.36.gate_proj.weight": "mtp.safetensors",
|
| 44471 |
+
"model.layers.92.mlp.experts.36.up_proj.weight": "mtp.safetensors",
|
| 44472 |
+
"model.layers.92.mlp.experts.37.down_proj.weight": "mtp.safetensors",
|
| 44473 |
+
"model.layers.92.mlp.experts.37.gate_proj.weight": "mtp.safetensors",
|
| 44474 |
+
"model.layers.92.mlp.experts.37.up_proj.weight": "mtp.safetensors",
|
| 44475 |
+
"model.layers.92.mlp.experts.38.down_proj.weight": "mtp.safetensors",
|
| 44476 |
+
"model.layers.92.mlp.experts.38.gate_proj.weight": "mtp.safetensors",
|
| 44477 |
+
"model.layers.92.mlp.experts.38.up_proj.weight": "mtp.safetensors",
|
| 44478 |
+
"model.layers.92.mlp.experts.39.down_proj.weight": "mtp.safetensors",
|
| 44479 |
+
"model.layers.92.mlp.experts.39.gate_proj.weight": "mtp.safetensors",
|
| 44480 |
+
"model.layers.92.mlp.experts.39.up_proj.weight": "mtp.safetensors",
|
| 44481 |
+
"model.layers.92.mlp.experts.4.down_proj.weight": "mtp.safetensors",
|
| 44482 |
+
"model.layers.92.mlp.experts.4.gate_proj.weight": "mtp.safetensors",
|
| 44483 |
+
"model.layers.92.mlp.experts.4.up_proj.weight": "mtp.safetensors",
|
| 44484 |
+
"model.layers.92.mlp.experts.40.down_proj.weight": "mtp.safetensors",
|
| 44485 |
+
"model.layers.92.mlp.experts.40.gate_proj.weight": "mtp.safetensors",
|
| 44486 |
+
"model.layers.92.mlp.experts.40.up_proj.weight": "mtp.safetensors",
|
| 44487 |
+
"model.layers.92.mlp.experts.41.down_proj.weight": "mtp.safetensors",
|
| 44488 |
+
"model.layers.92.mlp.experts.41.gate_proj.weight": "mtp.safetensors",
|
| 44489 |
+
"model.layers.92.mlp.experts.41.up_proj.weight": "mtp.safetensors",
|
| 44490 |
+
"model.layers.92.mlp.experts.42.down_proj.weight": "mtp.safetensors",
|
| 44491 |
+
"model.layers.92.mlp.experts.42.gate_proj.weight": "mtp.safetensors",
|
| 44492 |
+
"model.layers.92.mlp.experts.42.up_proj.weight": "mtp.safetensors",
|
| 44493 |
+
"model.layers.92.mlp.experts.43.down_proj.weight": "mtp.safetensors",
|
| 44494 |
+
"model.layers.92.mlp.experts.43.gate_proj.weight": "mtp.safetensors",
|
| 44495 |
+
"model.layers.92.mlp.experts.43.up_proj.weight": "mtp.safetensors",
|
| 44496 |
+
"model.layers.92.mlp.experts.44.down_proj.weight": "mtp.safetensors",
|
| 44497 |
+
"model.layers.92.mlp.experts.44.gate_proj.weight": "mtp.safetensors",
|
| 44498 |
+
"model.layers.92.mlp.experts.44.up_proj.weight": "mtp.safetensors",
|
| 44499 |
+
"model.layers.92.mlp.experts.45.down_proj.weight": "mtp.safetensors",
|
| 44500 |
+
"model.layers.92.mlp.experts.45.gate_proj.weight": "mtp.safetensors",
|
| 44501 |
+
"model.layers.92.mlp.experts.45.up_proj.weight": "mtp.safetensors",
|
| 44502 |
+
"model.layers.92.mlp.experts.46.down_proj.weight": "mtp.safetensors",
|
| 44503 |
+
"model.layers.92.mlp.experts.46.gate_proj.weight": "mtp.safetensors",
|
| 44504 |
+
"model.layers.92.mlp.experts.46.up_proj.weight": "mtp.safetensors",
|
| 44505 |
+
"model.layers.92.mlp.experts.47.down_proj.weight": "mtp.safetensors",
|
| 44506 |
+
"model.layers.92.mlp.experts.47.gate_proj.weight": "mtp.safetensors",
|
| 44507 |
+
"model.layers.92.mlp.experts.47.up_proj.weight": "mtp.safetensors",
|
| 44508 |
+
"model.layers.92.mlp.experts.48.down_proj.weight": "mtp.safetensors",
|
| 44509 |
+
"model.layers.92.mlp.experts.48.gate_proj.weight": "mtp.safetensors",
|
| 44510 |
+
"model.layers.92.mlp.experts.48.up_proj.weight": "mtp.safetensors",
|
| 44511 |
+
"model.layers.92.mlp.experts.49.down_proj.weight": "mtp.safetensors",
|
| 44512 |
+
"model.layers.92.mlp.experts.49.gate_proj.weight": "mtp.safetensors",
|
| 44513 |
+
"model.layers.92.mlp.experts.49.up_proj.weight": "mtp.safetensors",
|
| 44514 |
+
"model.layers.92.mlp.experts.5.down_proj.weight": "mtp.safetensors",
|
| 44515 |
+
"model.layers.92.mlp.experts.5.gate_proj.weight": "mtp.safetensors",
|
| 44516 |
+
"model.layers.92.mlp.experts.5.up_proj.weight": "mtp.safetensors",
|
| 44517 |
+
"model.layers.92.mlp.experts.50.down_proj.weight": "mtp.safetensors",
|
| 44518 |
+
"model.layers.92.mlp.experts.50.gate_proj.weight": "mtp.safetensors",
|
| 44519 |
+
"model.layers.92.mlp.experts.50.up_proj.weight": "mtp.safetensors",
|
| 44520 |
+
"model.layers.92.mlp.experts.51.down_proj.weight": "mtp.safetensors",
|
| 44521 |
+
"model.layers.92.mlp.experts.51.gate_proj.weight": "mtp.safetensors",
|
| 44522 |
+
"model.layers.92.mlp.experts.51.up_proj.weight": "mtp.safetensors",
|
| 44523 |
+
"model.layers.92.mlp.experts.52.down_proj.weight": "mtp.safetensors",
|
| 44524 |
+
"model.layers.92.mlp.experts.52.gate_proj.weight": "mtp.safetensors",
|
| 44525 |
+
"model.layers.92.mlp.experts.52.up_proj.weight": "mtp.safetensors",
|
| 44526 |
+
"model.layers.92.mlp.experts.53.down_proj.weight": "mtp.safetensors",
|
| 44527 |
+
"model.layers.92.mlp.experts.53.gate_proj.weight": "mtp.safetensors",
|
| 44528 |
+
"model.layers.92.mlp.experts.53.up_proj.weight": "mtp.safetensors",
|
| 44529 |
+
"model.layers.92.mlp.experts.54.down_proj.weight": "mtp.safetensors",
|
| 44530 |
+
"model.layers.92.mlp.experts.54.gate_proj.weight": "mtp.safetensors",
|
| 44531 |
+
"model.layers.92.mlp.experts.54.up_proj.weight": "mtp.safetensors",
|
| 44532 |
+
"model.layers.92.mlp.experts.55.down_proj.weight": "mtp.safetensors",
|
| 44533 |
+
"model.layers.92.mlp.experts.55.gate_proj.weight": "mtp.safetensors",
|
| 44534 |
+
"model.layers.92.mlp.experts.55.up_proj.weight": "mtp.safetensors",
|
| 44535 |
+
"model.layers.92.mlp.experts.56.down_proj.weight": "mtp.safetensors",
|
| 44536 |
+
"model.layers.92.mlp.experts.56.gate_proj.weight": "mtp.safetensors",
|
| 44537 |
+
"model.layers.92.mlp.experts.56.up_proj.weight": "mtp.safetensors",
|
| 44538 |
+
"model.layers.92.mlp.experts.57.down_proj.weight": "mtp.safetensors",
|
| 44539 |
+
"model.layers.92.mlp.experts.57.gate_proj.weight": "mtp.safetensors",
|
| 44540 |
+
"model.layers.92.mlp.experts.57.up_proj.weight": "mtp.safetensors",
|
| 44541 |
+
"model.layers.92.mlp.experts.58.down_proj.weight": "mtp.safetensors",
|
| 44542 |
+
"model.layers.92.mlp.experts.58.gate_proj.weight": "mtp.safetensors",
|
| 44543 |
+
"model.layers.92.mlp.experts.58.up_proj.weight": "mtp.safetensors",
|
| 44544 |
+
"model.layers.92.mlp.experts.59.down_proj.weight": "mtp.safetensors",
|
| 44545 |
+
"model.layers.92.mlp.experts.59.gate_proj.weight": "mtp.safetensors",
|
| 44546 |
+
"model.layers.92.mlp.experts.59.up_proj.weight": "mtp.safetensors",
|
| 44547 |
+
"model.layers.92.mlp.experts.6.down_proj.weight": "mtp.safetensors",
|
| 44548 |
+
"model.layers.92.mlp.experts.6.gate_proj.weight": "mtp.safetensors",
|
| 44549 |
+
"model.layers.92.mlp.experts.6.up_proj.weight": "mtp.safetensors",
|
| 44550 |
+
"model.layers.92.mlp.experts.60.down_proj.weight": "mtp.safetensors",
|
| 44551 |
+
"model.layers.92.mlp.experts.60.gate_proj.weight": "mtp.safetensors",
|
| 44552 |
+
"model.layers.92.mlp.experts.60.up_proj.weight": "mtp.safetensors",
|
| 44553 |
+
"model.layers.92.mlp.experts.61.down_proj.weight": "mtp.safetensors",
|
| 44554 |
+
"model.layers.92.mlp.experts.61.gate_proj.weight": "mtp.safetensors",
|
| 44555 |
+
"model.layers.92.mlp.experts.61.up_proj.weight": "mtp.safetensors",
|
| 44556 |
+
"model.layers.92.mlp.experts.62.down_proj.weight": "mtp.safetensors",
|
| 44557 |
+
"model.layers.92.mlp.experts.62.gate_proj.weight": "mtp.safetensors",
|
| 44558 |
+
"model.layers.92.mlp.experts.62.up_proj.weight": "mtp.safetensors",
|
| 44559 |
+
"model.layers.92.mlp.experts.63.down_proj.weight": "mtp.safetensors",
|
| 44560 |
+
"model.layers.92.mlp.experts.63.gate_proj.weight": "mtp.safetensors",
|
| 44561 |
+
"model.layers.92.mlp.experts.63.up_proj.weight": "mtp.safetensors",
|
| 44562 |
+
"model.layers.92.mlp.experts.64.down_proj.weight": "mtp.safetensors",
|
| 44563 |
+
"model.layers.92.mlp.experts.64.gate_proj.weight": "mtp.safetensors",
|
| 44564 |
+
"model.layers.92.mlp.experts.64.up_proj.weight": "mtp.safetensors",
|
| 44565 |
+
"model.layers.92.mlp.experts.65.down_proj.weight": "mtp.safetensors",
|
| 44566 |
+
"model.layers.92.mlp.experts.65.gate_proj.weight": "mtp.safetensors",
|
| 44567 |
+
"model.layers.92.mlp.experts.65.up_proj.weight": "mtp.safetensors",
|
| 44568 |
+
"model.layers.92.mlp.experts.66.down_proj.weight": "mtp.safetensors",
|
| 44569 |
+
"model.layers.92.mlp.experts.66.gate_proj.weight": "mtp.safetensors",
|
| 44570 |
+
"model.layers.92.mlp.experts.66.up_proj.weight": "mtp.safetensors",
|
| 44571 |
+
"model.layers.92.mlp.experts.67.down_proj.weight": "mtp.safetensors",
|
| 44572 |
+
"model.layers.92.mlp.experts.67.gate_proj.weight": "mtp.safetensors",
|
| 44573 |
+
"model.layers.92.mlp.experts.67.up_proj.weight": "mtp.safetensors",
|
| 44574 |
+
"model.layers.92.mlp.experts.68.down_proj.weight": "mtp.safetensors",
|
| 44575 |
+
"model.layers.92.mlp.experts.68.gate_proj.weight": "mtp.safetensors",
|
| 44576 |
+
"model.layers.92.mlp.experts.68.up_proj.weight": "mtp.safetensors",
|
| 44577 |
+
"model.layers.92.mlp.experts.69.down_proj.weight": "mtp.safetensors",
|
| 44578 |
+
"model.layers.92.mlp.experts.69.gate_proj.weight": "mtp.safetensors",
|
| 44579 |
+
"model.layers.92.mlp.experts.69.up_proj.weight": "mtp.safetensors",
|
| 44580 |
+
"model.layers.92.mlp.experts.7.down_proj.weight": "mtp.safetensors",
|
| 44581 |
+
"model.layers.92.mlp.experts.7.gate_proj.weight": "mtp.safetensors",
|
| 44582 |
+
"model.layers.92.mlp.experts.7.up_proj.weight": "mtp.safetensors",
|
| 44583 |
+
"model.layers.92.mlp.experts.70.down_proj.weight": "mtp.safetensors",
|
| 44584 |
+
"model.layers.92.mlp.experts.70.gate_proj.weight": "mtp.safetensors",
|
| 44585 |
+
"model.layers.92.mlp.experts.70.up_proj.weight": "mtp.safetensors",
|
| 44586 |
+
"model.layers.92.mlp.experts.71.down_proj.weight": "mtp.safetensors",
|
| 44587 |
+
"model.layers.92.mlp.experts.71.gate_proj.weight": "mtp.safetensors",
|
| 44588 |
+
"model.layers.92.mlp.experts.71.up_proj.weight": "mtp.safetensors",
|
| 44589 |
+
"model.layers.92.mlp.experts.72.down_proj.weight": "mtp.safetensors",
|
| 44590 |
+
"model.layers.92.mlp.experts.72.gate_proj.weight": "mtp.safetensors",
|
| 44591 |
+
"model.layers.92.mlp.experts.72.up_proj.weight": "mtp.safetensors",
|
| 44592 |
+
"model.layers.92.mlp.experts.73.down_proj.weight": "mtp.safetensors",
|
| 44593 |
+
"model.layers.92.mlp.experts.73.gate_proj.weight": "mtp.safetensors",
|
| 44594 |
+
"model.layers.92.mlp.experts.73.up_proj.weight": "mtp.safetensors",
|
| 44595 |
+
"model.layers.92.mlp.experts.74.down_proj.weight": "mtp.safetensors",
|
| 44596 |
+
"model.layers.92.mlp.experts.74.gate_proj.weight": "mtp.safetensors",
|
| 44597 |
+
"model.layers.92.mlp.experts.74.up_proj.weight": "mtp.safetensors",
|
| 44598 |
+
"model.layers.92.mlp.experts.75.down_proj.weight": "mtp.safetensors",
|
| 44599 |
+
"model.layers.92.mlp.experts.75.gate_proj.weight": "mtp.safetensors",
|
| 44600 |
+
"model.layers.92.mlp.experts.75.up_proj.weight": "mtp.safetensors",
|
| 44601 |
+
"model.layers.92.mlp.experts.76.down_proj.weight": "mtp.safetensors",
|
| 44602 |
+
"model.layers.92.mlp.experts.76.gate_proj.weight": "mtp.safetensors",
|
| 44603 |
+
"model.layers.92.mlp.experts.76.up_proj.weight": "mtp.safetensors",
|
| 44604 |
+
"model.layers.92.mlp.experts.77.down_proj.weight": "mtp.safetensors",
|
| 44605 |
+
"model.layers.92.mlp.experts.77.gate_proj.weight": "mtp.safetensors",
|
| 44606 |
+
"model.layers.92.mlp.experts.77.up_proj.weight": "mtp.safetensors",
|
| 44607 |
+
"model.layers.92.mlp.experts.78.down_proj.weight": "mtp.safetensors",
|
| 44608 |
+
"model.layers.92.mlp.experts.78.gate_proj.weight": "mtp.safetensors",
|
| 44609 |
+
"model.layers.92.mlp.experts.78.up_proj.weight": "mtp.safetensors",
|
| 44610 |
+
"model.layers.92.mlp.experts.79.down_proj.weight": "mtp.safetensors",
|
| 44611 |
+
"model.layers.92.mlp.experts.79.gate_proj.weight": "mtp.safetensors",
|
| 44612 |
+
"model.layers.92.mlp.experts.79.up_proj.weight": "mtp.safetensors",
|
| 44613 |
+
"model.layers.92.mlp.experts.8.down_proj.weight": "mtp.safetensors",
|
| 44614 |
+
"model.layers.92.mlp.experts.8.gate_proj.weight": "mtp.safetensors",
|
| 44615 |
+
"model.layers.92.mlp.experts.8.up_proj.weight": "mtp.safetensors",
|
| 44616 |
+
"model.layers.92.mlp.experts.80.down_proj.weight": "mtp.safetensors",
|
| 44617 |
+
"model.layers.92.mlp.experts.80.gate_proj.weight": "mtp.safetensors",
|
| 44618 |
+
"model.layers.92.mlp.experts.80.up_proj.weight": "mtp.safetensors",
|
| 44619 |
+
"model.layers.92.mlp.experts.81.down_proj.weight": "mtp.safetensors",
|
| 44620 |
+
"model.layers.92.mlp.experts.81.gate_proj.weight": "mtp.safetensors",
|
| 44621 |
+
"model.layers.92.mlp.experts.81.up_proj.weight": "mtp.safetensors",
|
| 44622 |
+
"model.layers.92.mlp.experts.82.down_proj.weight": "mtp.safetensors",
|
| 44623 |
+
"model.layers.92.mlp.experts.82.gate_proj.weight": "mtp.safetensors",
|
| 44624 |
+
"model.layers.92.mlp.experts.82.up_proj.weight": "mtp.safetensors",
|
| 44625 |
+
"model.layers.92.mlp.experts.83.down_proj.weight": "mtp.safetensors",
|
| 44626 |
+
"model.layers.92.mlp.experts.83.gate_proj.weight": "mtp.safetensors",
|
| 44627 |
+
"model.layers.92.mlp.experts.83.up_proj.weight": "mtp.safetensors",
|
| 44628 |
+
"model.layers.92.mlp.experts.84.down_proj.weight": "mtp.safetensors",
|
| 44629 |
+
"model.layers.92.mlp.experts.84.gate_proj.weight": "mtp.safetensors",
|
| 44630 |
+
"model.layers.92.mlp.experts.84.up_proj.weight": "mtp.safetensors",
|
| 44631 |
+
"model.layers.92.mlp.experts.85.down_proj.weight": "mtp.safetensors",
|
| 44632 |
+
"model.layers.92.mlp.experts.85.gate_proj.weight": "mtp.safetensors",
|
| 44633 |
+
"model.layers.92.mlp.experts.85.up_proj.weight": "mtp.safetensors",
|
| 44634 |
+
"model.layers.92.mlp.experts.86.down_proj.weight": "mtp.safetensors",
|
| 44635 |
+
"model.layers.92.mlp.experts.86.gate_proj.weight": "mtp.safetensors",
|
| 44636 |
+
"model.layers.92.mlp.experts.86.up_proj.weight": "mtp.safetensors",
|
| 44637 |
+
"model.layers.92.mlp.experts.87.down_proj.weight": "mtp.safetensors",
|
| 44638 |
+
"model.layers.92.mlp.experts.87.gate_proj.weight": "mtp.safetensors",
|
| 44639 |
+
"model.layers.92.mlp.experts.87.up_proj.weight": "mtp.safetensors",
|
| 44640 |
+
"model.layers.92.mlp.experts.88.down_proj.weight": "mtp.safetensors",
|
| 44641 |
+
"model.layers.92.mlp.experts.88.gate_proj.weight": "mtp.safetensors",
|
| 44642 |
+
"model.layers.92.mlp.experts.88.up_proj.weight": "mtp.safetensors",
|
| 44643 |
+
"model.layers.92.mlp.experts.89.down_proj.weight": "mtp.safetensors",
|
| 44644 |
+
"model.layers.92.mlp.experts.89.gate_proj.weight": "mtp.safetensors",
|
| 44645 |
+
"model.layers.92.mlp.experts.89.up_proj.weight": "mtp.safetensors",
|
| 44646 |
+
"model.layers.92.mlp.experts.9.down_proj.weight": "mtp.safetensors",
|
| 44647 |
+
"model.layers.92.mlp.experts.9.gate_proj.weight": "mtp.safetensors",
|
| 44648 |
+
"model.layers.92.mlp.experts.9.up_proj.weight": "mtp.safetensors",
|
| 44649 |
+
"model.layers.92.mlp.experts.90.down_proj.weight": "mtp.safetensors",
|
| 44650 |
+
"model.layers.92.mlp.experts.90.gate_proj.weight": "mtp.safetensors",
|
| 44651 |
+
"model.layers.92.mlp.experts.90.up_proj.weight": "mtp.safetensors",
|
| 44652 |
+
"model.layers.92.mlp.experts.91.down_proj.weight": "mtp.safetensors",
|
| 44653 |
+
"model.layers.92.mlp.experts.91.gate_proj.weight": "mtp.safetensors",
|
| 44654 |
+
"model.layers.92.mlp.experts.91.up_proj.weight": "mtp.safetensors",
|
| 44655 |
+
"model.layers.92.mlp.experts.92.down_proj.weight": "mtp.safetensors",
|
| 44656 |
+
"model.layers.92.mlp.experts.92.gate_proj.weight": "mtp.safetensors",
|
| 44657 |
+
"model.layers.92.mlp.experts.92.up_proj.weight": "mtp.safetensors",
|
| 44658 |
+
"model.layers.92.mlp.experts.93.down_proj.weight": "mtp.safetensors",
|
| 44659 |
+
"model.layers.92.mlp.experts.93.gate_proj.weight": "mtp.safetensors",
|
| 44660 |
+
"model.layers.92.mlp.experts.93.up_proj.weight": "mtp.safetensors",
|
| 44661 |
+
"model.layers.92.mlp.experts.94.down_proj.weight": "mtp.safetensors",
|
| 44662 |
+
"model.layers.92.mlp.experts.94.gate_proj.weight": "mtp.safetensors",
|
| 44663 |
+
"model.layers.92.mlp.experts.94.up_proj.weight": "mtp.safetensors",
|
| 44664 |
+
"model.layers.92.mlp.experts.95.down_proj.weight": "mtp.safetensors",
|
| 44665 |
+
"model.layers.92.mlp.experts.95.gate_proj.weight": "mtp.safetensors",
|
| 44666 |
+
"model.layers.92.mlp.experts.95.up_proj.weight": "mtp.safetensors",
|
| 44667 |
+
"model.layers.92.mlp.experts.96.down_proj.weight": "mtp.safetensors",
|
| 44668 |
+
"model.layers.92.mlp.experts.96.gate_proj.weight": "mtp.safetensors",
|
| 44669 |
+
"model.layers.92.mlp.experts.96.up_proj.weight": "mtp.safetensors",
|
| 44670 |
+
"model.layers.92.mlp.experts.97.down_proj.weight": "mtp.safetensors",
|
| 44671 |
+
"model.layers.92.mlp.experts.97.gate_proj.weight": "mtp.safetensors",
|
| 44672 |
+
"model.layers.92.mlp.experts.97.up_proj.weight": "mtp.safetensors",
|
| 44673 |
+
"model.layers.92.mlp.experts.98.down_proj.weight": "mtp.safetensors",
|
| 44674 |
+
"model.layers.92.mlp.experts.98.gate_proj.weight": "mtp.safetensors",
|
| 44675 |
+
"model.layers.92.mlp.experts.98.up_proj.weight": "mtp.safetensors",
|
| 44676 |
+
"model.layers.92.mlp.experts.99.down_proj.weight": "mtp.safetensors",
|
| 44677 |
+
"model.layers.92.mlp.experts.99.gate_proj.weight": "mtp.safetensors",
|
| 44678 |
+
"model.layers.92.mlp.experts.99.up_proj.weight": "mtp.safetensors",
|
| 44679 |
+
"model.layers.92.mlp.gate.e_score_correction_bias": "mtp.safetensors",
|
| 44680 |
+
"model.layers.92.mlp.gate.weight": "mtp.safetensors",
|
| 44681 |
+
"model.layers.92.mlp.shared_experts.down_proj.weight": "mtp.safetensors",
|
| 44682 |
+
"model.layers.92.mlp.shared_experts.gate_proj.weight": "mtp.safetensors",
|
| 44683 |
+
"model.layers.92.mlp.shared_experts.up_proj.weight": "mtp.safetensors",
|
| 44684 |
+
"model.layers.92.post_attention_layernorm.weight": "mtp.safetensors",
|
| 44685 |
+
"model.layers.92.self_attn.k_norm.weight": "mtp.safetensors",
|
| 44686 |
+
"model.layers.92.self_attn.k_proj.bias": "mtp.safetensors",
|
| 44687 |
+
"model.layers.92.self_attn.k_proj.weight": "mtp.safetensors",
|
| 44688 |
+
"model.layers.92.self_attn.o_proj.weight": "mtp.safetensors",
|
| 44689 |
+
"model.layers.92.self_attn.q_norm.weight": "mtp.safetensors",
|
| 44690 |
+
"model.layers.92.self_attn.q_proj.bias": "mtp.safetensors",
|
| 44691 |
+
"model.layers.92.self_attn.q_proj.weight": "mtp.safetensors",
|
| 44692 |
+
"model.layers.92.self_attn.v_proj.bias": "mtp.safetensors",
|
| 44693 |
+
"model.layers.92.self_attn.v_proj.weight": "mtp.safetensors",
|
| 44694 |
+
"model.layers.92.shared_head.norm.weight": "mtp.safetensors"
|
| 44695 |
}
|
| 44696 |
}
|
model-mtp.safetensors → mtp.safetensors
RENAMED
|
File without changes
|
tokenizer_config.json
CHANGED
|
@@ -324,5 +324,5 @@
|
|
| 324 |
"remove_space": false,
|
| 325 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 326 |
"unk_token": null,
|
| 327 |
-
"chat_template": "{#
|
| 328 |
}
|
|
|
|
| 324 |
"remove_space": false,
|
| 325 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 326 |
"unk_token": null,
|
| 327 |
+
"chat_template": "{# Unsloth template fixes #}\n[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{{ tool | tojson|string }}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>\n{{ visible_text(m.content) }}\n{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith(\"/nothink\")) else '' -}}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n{%- endif %}\n{%- if loop.index0 > ns.last_user_index and reasoning_content -%}\n{{ '\\n<think>' + reasoning_content.strip() + '</think>'}}\n{%- else -%}\n{{ '\\n<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ '\\n' + content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{ '\\n<tool_call>' + tc.name }}\n{% set _args = tc.arguments %}{%- if _args is mapping %}\n{% for k, v in _args|items %}\n<arg_key>{{ k }}</arg_key>\n<arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>\n{% endfor %}{%- endif %}\n</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' }}\n{%- endif %}\n{{- '\\n<tool_response>\\n' }}\n{{- m.content }}\n{{- '\\n</tool_response>' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n\n<tool_response>\n{{ tr.output if tr.output is defined else tr }}\n</tool_response>{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>\n{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '\\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}\n{%- endif -%}\n{# Copyright 2025-present Unsloth. Apache 2.0 License. #}"
|
| 328 |
}
|