Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +423 -0
- config.json +29 -0
- mergekit_config.yml +394 -0
- model-00001-of-00010.safetensors +3 -0
- model-00002-of-00010.safetensors +3 -0
- model-00003-of-00010.safetensors +3 -0
- model-00004-of-00010.safetensors +3 -0
- model-00005-of-00010.safetensors +3 -0
- model-00006-of-00010.safetensors +3 -0
- model-00007-of-00010.safetensors +3 -0
- model-00008-of-00010.safetensors +3 -0
- model-00009-of-00010.safetensors +3 -0
- model-00010-of-00010.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,423 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- unsloth/Mistral-Nemo-Base-2407
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- mergekit
|
7 |
+
- merge
|
8 |
+
|
9 |
+
---
|
10 |
+
# merge
|
11 |
+
|
12 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
13 |
+
|
14 |
+
## Merge Details
|
15 |
+
### Merge Method
|
16 |
+
|
17 |
+
This model was merged using the passthrough merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [unsloth/Mistral-Nemo-Base-2407](https://huggingface.co/unsloth/Mistral-Nemo-Base-2407)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
dtype: bfloat16
|
30 |
+
merge_method: passthrough
|
31 |
+
slices:
|
32 |
+
- sources:
|
33 |
+
- layer_range: [0, 2]
|
34 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
35 |
+
parameters:
|
36 |
+
scale:
|
37 |
+
- filter: o_proj
|
38 |
+
value: 0.0
|
39 |
+
- filter: down_proj
|
40 |
+
value: 0.0
|
41 |
+
- value: 1.0
|
42 |
+
- sources:
|
43 |
+
- layer_range: [1, 3]
|
44 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
45 |
+
parameters:
|
46 |
+
scale:
|
47 |
+
- filter: o_proj
|
48 |
+
value: 0.0
|
49 |
+
- filter: down_proj
|
50 |
+
value: 0.0
|
51 |
+
- value: 1.0
|
52 |
+
- sources:
|
53 |
+
- layer_range: [2, 4]
|
54 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
55 |
+
parameters:
|
56 |
+
scale:
|
57 |
+
- filter: o_proj
|
58 |
+
value: 0.0
|
59 |
+
- filter: down_proj
|
60 |
+
value: 0.0
|
61 |
+
- value: 1.0
|
62 |
+
- sources:
|
63 |
+
- layer_range: [3, 5]
|
64 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
65 |
+
parameters:
|
66 |
+
scale:
|
67 |
+
- filter: o_proj
|
68 |
+
value: 0.0
|
69 |
+
- filter: down_proj
|
70 |
+
value: 0.0
|
71 |
+
- value: 1.0
|
72 |
+
# 以下是新增的層
|
73 |
+
- sources:
|
74 |
+
- layer_range: [4, 6]
|
75 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
76 |
+
parameters:
|
77 |
+
scale:
|
78 |
+
- filter: o_proj
|
79 |
+
value: 0.0
|
80 |
+
- filter: down_proj
|
81 |
+
value: 0.0
|
82 |
+
- value: 1.0
|
83 |
+
- sources:
|
84 |
+
- layer_range: [5, 7]
|
85 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
86 |
+
parameters:
|
87 |
+
scale:
|
88 |
+
- filter: o_proj
|
89 |
+
value: 0.0
|
90 |
+
- filter: down_proj
|
91 |
+
value: 0.0
|
92 |
+
- value: 1.0
|
93 |
+
- sources:
|
94 |
+
- layer_range: [6, 8]
|
95 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
96 |
+
parameters:
|
97 |
+
scale:
|
98 |
+
- filter: o_proj
|
99 |
+
value: 0.0
|
100 |
+
- filter: down_proj
|
101 |
+
value: 0.0
|
102 |
+
- value: 1.0
|
103 |
+
- sources:
|
104 |
+
- layer_range: [7, 9]
|
105 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
106 |
+
parameters:
|
107 |
+
scale:
|
108 |
+
- filter: o_proj
|
109 |
+
value: 0.0
|
110 |
+
- filter: down_proj
|
111 |
+
value: 0.0
|
112 |
+
- value: 1.0
|
113 |
+
- sources:
|
114 |
+
- layer_range: [8, 10]
|
115 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
116 |
+
parameters:
|
117 |
+
scale:
|
118 |
+
- filter: o_proj
|
119 |
+
value: 0.0
|
120 |
+
- filter: down_proj
|
121 |
+
value: 0.0
|
122 |
+
- value: 1.0
|
123 |
+
- sources:
|
124 |
+
- layer_range: [9, 11]
|
125 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
126 |
+
parameters:
|
127 |
+
scale:
|
128 |
+
- filter: o_proj
|
129 |
+
value: 0.0
|
130 |
+
- filter: down_proj
|
131 |
+
value: 0.0
|
132 |
+
- value: 1.0
|
133 |
+
- sources:
|
134 |
+
- layer_range: [10, 12]
|
135 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
136 |
+
parameters:
|
137 |
+
scale:
|
138 |
+
- filter: o_proj
|
139 |
+
value: 0.0
|
140 |
+
- filter: down_proj
|
141 |
+
value: 0.0
|
142 |
+
- value: 1.0
|
143 |
+
- sources:
|
144 |
+
- layer_range: [11, 13]
|
145 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
146 |
+
parameters:
|
147 |
+
scale:
|
148 |
+
- filter: o_proj
|
149 |
+
value: 0.0
|
150 |
+
- filter: down_proj
|
151 |
+
value: 0.0
|
152 |
+
- value: 1.0
|
153 |
+
- sources:
|
154 |
+
- layer_range: [12, 14]
|
155 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
156 |
+
parameters:
|
157 |
+
scale:
|
158 |
+
- filter: o_proj
|
159 |
+
value: 0.0
|
160 |
+
- filter: down_proj
|
161 |
+
value: 0.0
|
162 |
+
- value: 1.0
|
163 |
+
- sources:
|
164 |
+
- layer_range: [13, 15]
|
165 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
166 |
+
parameters:
|
167 |
+
scale:
|
168 |
+
- filter: o_proj
|
169 |
+
value: 0.0
|
170 |
+
- filter: down_proj
|
171 |
+
value: 0.0
|
172 |
+
- value: 1.0
|
173 |
+
- sources:
|
174 |
+
- layer_range: [14, 16]
|
175 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
176 |
+
parameters:
|
177 |
+
scale:
|
178 |
+
- filter: o_proj
|
179 |
+
value: 0.0
|
180 |
+
- filter: down_proj
|
181 |
+
value: 0.0
|
182 |
+
- value: 1.0
|
183 |
+
- sources:
|
184 |
+
- layer_range: [15, 17]
|
185 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
186 |
+
parameters:
|
187 |
+
scale:
|
188 |
+
- filter: o_proj
|
189 |
+
value: 0.0
|
190 |
+
- filter: down_proj
|
191 |
+
value: 0.0
|
192 |
+
- value: 1.0
|
193 |
+
- sources:
|
194 |
+
- layer_range: [16, 18]
|
195 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
196 |
+
parameters:
|
197 |
+
scale:
|
198 |
+
- filter: o_proj
|
199 |
+
value: 0.0
|
200 |
+
- filter: down_proj
|
201 |
+
value: 0.0
|
202 |
+
- value: 1.0
|
203 |
+
- sources:
|
204 |
+
- layer_range: [17, 19]
|
205 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
206 |
+
parameters:
|
207 |
+
scale:
|
208 |
+
- filter: o_proj
|
209 |
+
value: 0.0
|
210 |
+
- filter: down_proj
|
211 |
+
value: 0.0
|
212 |
+
- value: 1.0
|
213 |
+
- sources:
|
214 |
+
- layer_range: [18, 20]
|
215 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
216 |
+
parameters:
|
217 |
+
scale:
|
218 |
+
- filter: o_proj
|
219 |
+
value: 0.0
|
220 |
+
- filter: down_proj
|
221 |
+
value: 0.0
|
222 |
+
- value: 1.0
|
223 |
+
- sources:
|
224 |
+
- layer_range: [19, 21]
|
225 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
226 |
+
parameters:
|
227 |
+
scale:
|
228 |
+
- filter: o_proj
|
229 |
+
value: 0.0
|
230 |
+
- filter: down_proj
|
231 |
+
value: 0.0
|
232 |
+
- value: 1.0
|
233 |
+
- sources:
|
234 |
+
- layer_range: [20, 22]
|
235 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
236 |
+
parameters:
|
237 |
+
scale:
|
238 |
+
- filter: o_proj
|
239 |
+
value: 0.0
|
240 |
+
- filter: down_proj
|
241 |
+
value: 0.0
|
242 |
+
- value: 1.0
|
243 |
+
- sources:
|
244 |
+
- layer_range: [21, 23]
|
245 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
246 |
+
parameters:
|
247 |
+
scale:
|
248 |
+
- filter: o_proj
|
249 |
+
value: 0.0
|
250 |
+
- filter: down_proj
|
251 |
+
value: 0.0
|
252 |
+
- value: 1.0
|
253 |
+
- sources:
|
254 |
+
- layer_range: [22, 24]
|
255 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
256 |
+
parameters:
|
257 |
+
scale:
|
258 |
+
- filter: o_proj
|
259 |
+
value: 0.0
|
260 |
+
- filter: down_proj
|
261 |
+
value: 0.0
|
262 |
+
- value: 1.0
|
263 |
+
- sources:
|
264 |
+
- layer_range: [23, 25]
|
265 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
266 |
+
parameters:
|
267 |
+
scale:
|
268 |
+
- filter: o_proj
|
269 |
+
value: 0.0
|
270 |
+
- filter: down_proj
|
271 |
+
value: 0.0
|
272 |
+
- value: 1.0
|
273 |
+
- sources:
|
274 |
+
- layer_range: [24, 26]
|
275 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
276 |
+
parameters:
|
277 |
+
scale:
|
278 |
+
- filter: o_proj
|
279 |
+
value: 0.0
|
280 |
+
- filter: down_proj
|
281 |
+
value: 0.0
|
282 |
+
- value: 1.0
|
283 |
+
- sources:
|
284 |
+
- layer_range: [25, 27]
|
285 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
286 |
+
parameters:
|
287 |
+
scale:
|
288 |
+
- filter: o_proj
|
289 |
+
value: 0.0
|
290 |
+
- filter: down_proj
|
291 |
+
value: 0.0
|
292 |
+
- value: 1.0
|
293 |
+
- sources:
|
294 |
+
- layer_range: [26, 28]
|
295 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
296 |
+
parameters:
|
297 |
+
scale:
|
298 |
+
- filter: o_proj
|
299 |
+
value: 0.0
|
300 |
+
- filter: down_proj
|
301 |
+
value: 0.0
|
302 |
+
- value: 1.0
|
303 |
+
- sources:
|
304 |
+
- layer_range: [27, 29]
|
305 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
306 |
+
parameters:
|
307 |
+
scale:
|
308 |
+
- filter: o_proj
|
309 |
+
value: 0.0
|
310 |
+
- filter: down_proj
|
311 |
+
value: 0.0
|
312 |
+
- value: 1.0
|
313 |
+
- sources:
|
314 |
+
- layer_range: [28, 30]
|
315 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
316 |
+
parameters:
|
317 |
+
scale:
|
318 |
+
- filter: o_proj
|
319 |
+
value: 0.0
|
320 |
+
- filter: down_proj
|
321 |
+
value: 0.0
|
322 |
+
- value: 1.0
|
323 |
+
- sources:
|
324 |
+
- layer_range: [29, 31]
|
325 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
326 |
+
parameters:
|
327 |
+
scale:
|
328 |
+
- filter: o_proj
|
329 |
+
value: 0.0
|
330 |
+
- filter: down_proj
|
331 |
+
value: 0.0
|
332 |
+
- value: 1.0
|
333 |
+
- sources:
|
334 |
+
- layer_range: [30, 32]
|
335 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
336 |
+
parameters:
|
337 |
+
scale:
|
338 |
+
- filter: o_proj
|
339 |
+
value: 0.0
|
340 |
+
- filter: down_proj
|
341 |
+
value: 0.0
|
342 |
+
- value: 1.0
|
343 |
+
- sources:
|
344 |
+
- layer_range: [31, 33]
|
345 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
346 |
+
parameters:
|
347 |
+
scale:
|
348 |
+
- filter: o_proj
|
349 |
+
value: 0.0
|
350 |
+
- filter: down_proj
|
351 |
+
value: 0.0
|
352 |
+
- value: 1.0
|
353 |
+
- sources:
|
354 |
+
- layer_range: [32, 34]
|
355 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
356 |
+
parameters:
|
357 |
+
scale:
|
358 |
+
- filter: o_proj
|
359 |
+
value: 0.0
|
360 |
+
- filter: down_proj
|
361 |
+
value: 0.0
|
362 |
+
- value: 1.0
|
363 |
+
- sources:
|
364 |
+
- layer_range: [33, 35]
|
365 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
366 |
+
parameters:
|
367 |
+
scale:
|
368 |
+
- filter: o_proj
|
369 |
+
value: 0.0
|
370 |
+
- filter: down_proj
|
371 |
+
value: 0.0
|
372 |
+
- value: 1.0
|
373 |
+
- sources:
|
374 |
+
- layer_range: [34, 36]
|
375 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
376 |
+
parameters:
|
377 |
+
scale:
|
378 |
+
- filter: o_proj
|
379 |
+
value: 0.0
|
380 |
+
- filter: down_proj
|
381 |
+
value: 0.0
|
382 |
+
- value: 1.0
|
383 |
+
- sources:
|
384 |
+
- layer_range: [35, 37]
|
385 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
386 |
+
parameters:
|
387 |
+
scale:
|
388 |
+
- filter: o_proj
|
389 |
+
value: 0.0
|
390 |
+
- filter: down_proj
|
391 |
+
value: 0.0
|
392 |
+
- value: 1.0
|
393 |
+
- sources:
|
394 |
+
- layer_range: [36, 38]
|
395 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
396 |
+
parameters:
|
397 |
+
scale:
|
398 |
+
- filter: o_proj
|
399 |
+
value: 0.0
|
400 |
+
- filter: down_proj
|
401 |
+
value: 0.0
|
402 |
+
- value: 1.0
|
403 |
+
- sources:
|
404 |
+
- layer_range: [37, 39]
|
405 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
406 |
+
parameters:
|
407 |
+
scale:
|
408 |
+
- filter: o_proj
|
409 |
+
value: 0.0
|
410 |
+
- filter: down_proj
|
411 |
+
value: 0.0
|
412 |
+
- value: 1.0
|
413 |
+
- sources:
|
414 |
+
- layer_range: [38, 40]
|
415 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
416 |
+
parameters:
|
417 |
+
scale:
|
418 |
+
- filter: o_proj
|
419 |
+
value: 0.0
|
420 |
+
- filter: down_proj
|
421 |
+
value: 0.0
|
422 |
+
- value: 1.0
|
423 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unsloth/Mistral-Nemo-Base-2407",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 1024000,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 78,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 10,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.45.1",
|
26 |
+
"unsloth_version": "2024.9",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 131072
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
dtype: bfloat16
|
2 |
+
merge_method: passthrough
|
3 |
+
slices:
|
4 |
+
- sources:
|
5 |
+
- layer_range: [0, 2]
|
6 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
7 |
+
parameters:
|
8 |
+
scale:
|
9 |
+
- filter: o_proj
|
10 |
+
value: 0.0
|
11 |
+
- filter: down_proj
|
12 |
+
value: 0.0
|
13 |
+
- value: 1.0
|
14 |
+
- sources:
|
15 |
+
- layer_range: [1, 3]
|
16 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
17 |
+
parameters:
|
18 |
+
scale:
|
19 |
+
- filter: o_proj
|
20 |
+
value: 0.0
|
21 |
+
- filter: down_proj
|
22 |
+
value: 0.0
|
23 |
+
- value: 1.0
|
24 |
+
- sources:
|
25 |
+
- layer_range: [2, 4]
|
26 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
27 |
+
parameters:
|
28 |
+
scale:
|
29 |
+
- filter: o_proj
|
30 |
+
value: 0.0
|
31 |
+
- filter: down_proj
|
32 |
+
value: 0.0
|
33 |
+
- value: 1.0
|
34 |
+
- sources:
|
35 |
+
- layer_range: [3, 5]
|
36 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
37 |
+
parameters:
|
38 |
+
scale:
|
39 |
+
- filter: o_proj
|
40 |
+
value: 0.0
|
41 |
+
- filter: down_proj
|
42 |
+
value: 0.0
|
43 |
+
- value: 1.0
|
44 |
+
# 以下是新增的層
|
45 |
+
- sources:
|
46 |
+
- layer_range: [4, 6]
|
47 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
48 |
+
parameters:
|
49 |
+
scale:
|
50 |
+
- filter: o_proj
|
51 |
+
value: 0.0
|
52 |
+
- filter: down_proj
|
53 |
+
value: 0.0
|
54 |
+
- value: 1.0
|
55 |
+
- sources:
|
56 |
+
- layer_range: [5, 7]
|
57 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
58 |
+
parameters:
|
59 |
+
scale:
|
60 |
+
- filter: o_proj
|
61 |
+
value: 0.0
|
62 |
+
- filter: down_proj
|
63 |
+
value: 0.0
|
64 |
+
- value: 1.0
|
65 |
+
- sources:
|
66 |
+
- layer_range: [6, 8]
|
67 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
68 |
+
parameters:
|
69 |
+
scale:
|
70 |
+
- filter: o_proj
|
71 |
+
value: 0.0
|
72 |
+
- filter: down_proj
|
73 |
+
value: 0.0
|
74 |
+
- value: 1.0
|
75 |
+
- sources:
|
76 |
+
- layer_range: [7, 9]
|
77 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
78 |
+
parameters:
|
79 |
+
scale:
|
80 |
+
- filter: o_proj
|
81 |
+
value: 0.0
|
82 |
+
- filter: down_proj
|
83 |
+
value: 0.0
|
84 |
+
- value: 1.0
|
85 |
+
- sources:
|
86 |
+
- layer_range: [8, 10]
|
87 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
88 |
+
parameters:
|
89 |
+
scale:
|
90 |
+
- filter: o_proj
|
91 |
+
value: 0.0
|
92 |
+
- filter: down_proj
|
93 |
+
value: 0.0
|
94 |
+
- value: 1.0
|
95 |
+
- sources:
|
96 |
+
- layer_range: [9, 11]
|
97 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
98 |
+
parameters:
|
99 |
+
scale:
|
100 |
+
- filter: o_proj
|
101 |
+
value: 0.0
|
102 |
+
- filter: down_proj
|
103 |
+
value: 0.0
|
104 |
+
- value: 1.0
|
105 |
+
- sources:
|
106 |
+
- layer_range: [10, 12]
|
107 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
108 |
+
parameters:
|
109 |
+
scale:
|
110 |
+
- filter: o_proj
|
111 |
+
value: 0.0
|
112 |
+
- filter: down_proj
|
113 |
+
value: 0.0
|
114 |
+
- value: 1.0
|
115 |
+
- sources:
|
116 |
+
- layer_range: [11, 13]
|
117 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
118 |
+
parameters:
|
119 |
+
scale:
|
120 |
+
- filter: o_proj
|
121 |
+
value: 0.0
|
122 |
+
- filter: down_proj
|
123 |
+
value: 0.0
|
124 |
+
- value: 1.0
|
125 |
+
- sources:
|
126 |
+
- layer_range: [12, 14]
|
127 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
128 |
+
parameters:
|
129 |
+
scale:
|
130 |
+
- filter: o_proj
|
131 |
+
value: 0.0
|
132 |
+
- filter: down_proj
|
133 |
+
value: 0.0
|
134 |
+
- value: 1.0
|
135 |
+
- sources:
|
136 |
+
- layer_range: [13, 15]
|
137 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
138 |
+
parameters:
|
139 |
+
scale:
|
140 |
+
- filter: o_proj
|
141 |
+
value: 0.0
|
142 |
+
- filter: down_proj
|
143 |
+
value: 0.0
|
144 |
+
- value: 1.0
|
145 |
+
- sources:
|
146 |
+
- layer_range: [14, 16]
|
147 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
148 |
+
parameters:
|
149 |
+
scale:
|
150 |
+
- filter: o_proj
|
151 |
+
value: 0.0
|
152 |
+
- filter: down_proj
|
153 |
+
value: 0.0
|
154 |
+
- value: 1.0
|
155 |
+
- sources:
|
156 |
+
- layer_range: [15, 17]
|
157 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
158 |
+
parameters:
|
159 |
+
scale:
|
160 |
+
- filter: o_proj
|
161 |
+
value: 0.0
|
162 |
+
- filter: down_proj
|
163 |
+
value: 0.0
|
164 |
+
- value: 1.0
|
165 |
+
- sources:
|
166 |
+
- layer_range: [16, 18]
|
167 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
168 |
+
parameters:
|
169 |
+
scale:
|
170 |
+
- filter: o_proj
|
171 |
+
value: 0.0
|
172 |
+
- filter: down_proj
|
173 |
+
value: 0.0
|
174 |
+
- value: 1.0
|
175 |
+
- sources:
|
176 |
+
- layer_range: [17, 19]
|
177 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
178 |
+
parameters:
|
179 |
+
scale:
|
180 |
+
- filter: o_proj
|
181 |
+
value: 0.0
|
182 |
+
- filter: down_proj
|
183 |
+
value: 0.0
|
184 |
+
- value: 1.0
|
185 |
+
- sources:
|
186 |
+
- layer_range: [18, 20]
|
187 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
188 |
+
parameters:
|
189 |
+
scale:
|
190 |
+
- filter: o_proj
|
191 |
+
value: 0.0
|
192 |
+
- filter: down_proj
|
193 |
+
value: 0.0
|
194 |
+
- value: 1.0
|
195 |
+
- sources:
|
196 |
+
- layer_range: [19, 21]
|
197 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
198 |
+
parameters:
|
199 |
+
scale:
|
200 |
+
- filter: o_proj
|
201 |
+
value: 0.0
|
202 |
+
- filter: down_proj
|
203 |
+
value: 0.0
|
204 |
+
- value: 1.0
|
205 |
+
- sources:
|
206 |
+
- layer_range: [20, 22]
|
207 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
208 |
+
parameters:
|
209 |
+
scale:
|
210 |
+
- filter: o_proj
|
211 |
+
value: 0.0
|
212 |
+
- filter: down_proj
|
213 |
+
value: 0.0
|
214 |
+
- value: 1.0
|
215 |
+
- sources:
|
216 |
+
- layer_range: [21, 23]
|
217 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
218 |
+
parameters:
|
219 |
+
scale:
|
220 |
+
- filter: o_proj
|
221 |
+
value: 0.0
|
222 |
+
- filter: down_proj
|
223 |
+
value: 0.0
|
224 |
+
- value: 1.0
|
225 |
+
- sources:
|
226 |
+
- layer_range: [22, 24]
|
227 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
228 |
+
parameters:
|
229 |
+
scale:
|
230 |
+
- filter: o_proj
|
231 |
+
value: 0.0
|
232 |
+
- filter: down_proj
|
233 |
+
value: 0.0
|
234 |
+
- value: 1.0
|
235 |
+
- sources:
|
236 |
+
- layer_range: [23, 25]
|
237 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
238 |
+
parameters:
|
239 |
+
scale:
|
240 |
+
- filter: o_proj
|
241 |
+
value: 0.0
|
242 |
+
- filter: down_proj
|
243 |
+
value: 0.0
|
244 |
+
- value: 1.0
|
245 |
+
- sources:
|
246 |
+
- layer_range: [24, 26]
|
247 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
248 |
+
parameters:
|
249 |
+
scale:
|
250 |
+
- filter: o_proj
|
251 |
+
value: 0.0
|
252 |
+
- filter: down_proj
|
253 |
+
value: 0.0
|
254 |
+
- value: 1.0
|
255 |
+
- sources:
|
256 |
+
- layer_range: [25, 27]
|
257 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
258 |
+
parameters:
|
259 |
+
scale:
|
260 |
+
- filter: o_proj
|
261 |
+
value: 0.0
|
262 |
+
- filter: down_proj
|
263 |
+
value: 0.0
|
264 |
+
- value: 1.0
|
265 |
+
- sources:
|
266 |
+
- layer_range: [26, 28]
|
267 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
268 |
+
parameters:
|
269 |
+
scale:
|
270 |
+
- filter: o_proj
|
271 |
+
value: 0.0
|
272 |
+
- filter: down_proj
|
273 |
+
value: 0.0
|
274 |
+
- value: 1.0
|
275 |
+
- sources:
|
276 |
+
- layer_range: [27, 29]
|
277 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
278 |
+
parameters:
|
279 |
+
scale:
|
280 |
+
- filter: o_proj
|
281 |
+
value: 0.0
|
282 |
+
- filter: down_proj
|
283 |
+
value: 0.0
|
284 |
+
- value: 1.0
|
285 |
+
- sources:
|
286 |
+
- layer_range: [28, 30]
|
287 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
288 |
+
parameters:
|
289 |
+
scale:
|
290 |
+
- filter: o_proj
|
291 |
+
value: 0.0
|
292 |
+
- filter: down_proj
|
293 |
+
value: 0.0
|
294 |
+
- value: 1.0
|
295 |
+
- sources:
|
296 |
+
- layer_range: [29, 31]
|
297 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
298 |
+
parameters:
|
299 |
+
scale:
|
300 |
+
- filter: o_proj
|
301 |
+
value: 0.0
|
302 |
+
- filter: down_proj
|
303 |
+
value: 0.0
|
304 |
+
- value: 1.0
|
305 |
+
- sources:
|
306 |
+
- layer_range: [30, 32]
|
307 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
308 |
+
parameters:
|
309 |
+
scale:
|
310 |
+
- filter: o_proj
|
311 |
+
value: 0.0
|
312 |
+
- filter: down_proj
|
313 |
+
value: 0.0
|
314 |
+
- value: 1.0
|
315 |
+
- sources:
|
316 |
+
- layer_range: [31, 33]
|
317 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
318 |
+
parameters:
|
319 |
+
scale:
|
320 |
+
- filter: o_proj
|
321 |
+
value: 0.0
|
322 |
+
- filter: down_proj
|
323 |
+
value: 0.0
|
324 |
+
- value: 1.0
|
325 |
+
- sources:
|
326 |
+
- layer_range: [32, 34]
|
327 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
328 |
+
parameters:
|
329 |
+
scale:
|
330 |
+
- filter: o_proj
|
331 |
+
value: 0.0
|
332 |
+
- filter: down_proj
|
333 |
+
value: 0.0
|
334 |
+
- value: 1.0
|
335 |
+
- sources:
|
336 |
+
- layer_range: [33, 35]
|
337 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
338 |
+
parameters:
|
339 |
+
scale:
|
340 |
+
- filter: o_proj
|
341 |
+
value: 0.0
|
342 |
+
- filter: down_proj
|
343 |
+
value: 0.0
|
344 |
+
- value: 1.0
|
345 |
+
- sources:
|
346 |
+
- layer_range: [34, 36]
|
347 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
348 |
+
parameters:
|
349 |
+
scale:
|
350 |
+
- filter: o_proj
|
351 |
+
value: 0.0
|
352 |
+
- filter: down_proj
|
353 |
+
value: 0.0
|
354 |
+
- value: 1.0
|
355 |
+
- sources:
|
356 |
+
- layer_range: [35, 37]
|
357 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
358 |
+
parameters:
|
359 |
+
scale:
|
360 |
+
- filter: o_proj
|
361 |
+
value: 0.0
|
362 |
+
- filter: down_proj
|
363 |
+
value: 0.0
|
364 |
+
- value: 1.0
|
365 |
+
- sources:
|
366 |
+
- layer_range: [36, 38]
|
367 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
368 |
+
parameters:
|
369 |
+
scale:
|
370 |
+
- filter: o_proj
|
371 |
+
value: 0.0
|
372 |
+
- filter: down_proj
|
373 |
+
value: 0.0
|
374 |
+
- value: 1.0
|
375 |
+
- sources:
|
376 |
+
- layer_range: [37, 39]
|
377 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
378 |
+
parameters:
|
379 |
+
scale:
|
380 |
+
- filter: o_proj
|
381 |
+
value: 0.0
|
382 |
+
- filter: down_proj
|
383 |
+
value: 0.0
|
384 |
+
- value: 1.0
|
385 |
+
- sources:
|
386 |
+
- layer_range: [38, 40]
|
387 |
+
model: unsloth/Mistral-Nemo-Base-2407
|
388 |
+
parameters:
|
389 |
+
scale:
|
390 |
+
- filter: o_proj
|
391 |
+
value: 0.0
|
392 |
+
- filter: down_proj
|
393 |
+
value: 0.0
|
394 |
+
- value: 1.0
|
model-00001-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b848e9c197e4f1ecb4d46f86505432e6657a6000c49bfea0a457218aff074e91
|
3 |
+
size 4907421648
|
model-00002-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72340cc1562b95489b5c883f154b089e796739be494969bbf21b32601ee9b3e1
|
3 |
+
size 4865607480
|
model-00003-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9207bb434efd418b29e9f6f351b21246a6142643ff472d295cad4921baec52
|
3 |
+
size 4949451440
|
model-00004-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cc3aa9f9ac02ee99a076c900968356c7a6a17e620a4f6fe821d48c46443b564
|
3 |
+
size 4865607456
|
model-00005-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23ad1908b369df31a5853a6ac260784ab1b509df32eac3b363213f41da95a580
|
3 |
+
size 4949451440
|
model-00006-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c18ecb76ca5015f39ba66e463937ede712ca7946d3a8935649475a091abacef4
|
3 |
+
size 4865607456
|
model-00007-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2370407681acc61d20b8d5ce8765a43b5d1e63fffda2d92335a4ed0f2671b5f
|
3 |
+
size 4949451440
|
model-00008-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cff3aa06bfebed88ee590297b992dbd0fc8fd932191c108a042441c35442e4e2
|
3 |
+
size 4907529456
|
model-00009-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40e612a57ee78022f5736c7d98864b44dcf5b3e4a07db1e1ad3e4dbfc1fba868
|
3 |
+
size 4865607464
|
model-00010-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:310d195dac20e5fdba4e1bbcfbfedfcced5b1d772293e9e48d65827ef606b09d
|
3 |
+
size 1090551736
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 45216204800}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.46.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.45.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.47.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.49.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.51.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.54.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.53.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.55.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.59.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.62.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.61.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.63.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.65.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.67.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.70.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.69.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.71.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.73.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.75.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
|
3 |
+
size 17078292
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|