Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +512 -0
- added_tokens.json +24 -0
- config.json +28 -0
- mergekit_config.yml +483 -0
- merges.txt +0 -0
- model-00001-of-00060.safetensors +3 -0
- model-00002-of-00060.safetensors +3 -0
- model-00003-of-00060.safetensors +3 -0
- model-00004-of-00060.safetensors +3 -0
- model-00005-of-00060.safetensors +3 -0
- model-00006-of-00060.safetensors +3 -0
- model-00007-of-00060.safetensors +3 -0
- model-00008-of-00060.safetensors +3 -0
- model-00009-of-00060.safetensors +3 -0
- model-00010-of-00060.safetensors +3 -0
- model-00011-of-00060.safetensors +3 -0
- model-00012-of-00060.safetensors +3 -0
- model-00013-of-00060.safetensors +3 -0
- model-00014-of-00060.safetensors +3 -0
- model-00015-of-00060.safetensors +3 -0
- model-00016-of-00060.safetensors +3 -0
- model-00017-of-00060.safetensors +3 -0
- model-00018-of-00060.safetensors +3 -0
- model-00019-of-00060.safetensors +3 -0
- model-00020-of-00060.safetensors +3 -0
- model-00021-of-00060.safetensors +3 -0
- model-00022-of-00060.safetensors +3 -0
- model-00023-of-00060.safetensors +3 -0
- model-00024-of-00060.safetensors +3 -0
- model-00025-of-00060.safetensors +3 -0
- model-00026-of-00060.safetensors +3 -0
- model-00027-of-00060.safetensors +3 -0
- model-00028-of-00060.safetensors +3 -0
- model-00029-of-00060.safetensors +3 -0
- model-00030-of-00060.safetensors +3 -0
- model-00031-of-00060.safetensors +3 -0
- model-00032-of-00060.safetensors +3 -0
- model-00033-of-00060.safetensors +3 -0
- model-00034-of-00060.safetensors +3 -0
- model-00035-of-00060.safetensors +3 -0
- model-00036-of-00060.safetensors +3 -0
- model-00037-of-00060.safetensors +3 -0
- model-00038-of-00060.safetensors +3 -0
- model-00039-of-00060.safetensors +3 -0
- model-00040-of-00060.safetensors +3 -0
- model-00041-of-00060.safetensors +3 -0
- model-00042-of-00060.safetensors +3 -0
- model-00043-of-00060.safetensors +3 -0
- model-00044-of-00060.safetensors +3 -0
- model-00045-of-00060.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,512 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2.5-72B-Instruct
|
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 |
+
* [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
slices:
|
30 |
+
- sources:
|
31 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
32 |
+
layer_range: [0, 1]
|
33 |
+
- sources:
|
34 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
35 |
+
layer_range: [0, 1]
|
36 |
+
- sources:
|
37 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
38 |
+
layer_range: [1, 2]
|
39 |
+
- sources:
|
40 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
41 |
+
layer_range: [1, 2]
|
42 |
+
- sources:
|
43 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
44 |
+
layer_range: [2, 3]
|
45 |
+
- sources:
|
46 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
47 |
+
layer_range: [2, 3]
|
48 |
+
- sources:
|
49 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
50 |
+
layer_range: [3, 4]
|
51 |
+
- sources:
|
52 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
53 |
+
layer_range: [3, 4]
|
54 |
+
- sources:
|
55 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
56 |
+
layer_range: [4, 5]
|
57 |
+
- sources:
|
58 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
59 |
+
layer_range: [4, 5]
|
60 |
+
- sources:
|
61 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
62 |
+
layer_range: [5, 6]
|
63 |
+
- sources:
|
64 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
65 |
+
layer_range: [5, 6]
|
66 |
+
- sources:
|
67 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
68 |
+
layer_range: [6, 7]
|
69 |
+
- sources:
|
70 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
71 |
+
layer_range: [6, 7]
|
72 |
+
- sources:
|
73 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
74 |
+
layer_range: [7, 8]
|
75 |
+
- sources:
|
76 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
77 |
+
layer_range: [7, 8]
|
78 |
+
- sources:
|
79 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
80 |
+
layer_range: [8, 9]
|
81 |
+
- sources:
|
82 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
83 |
+
layer_range: [8, 9]
|
84 |
+
- sources:
|
85 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
86 |
+
layer_range: [9, 10]
|
87 |
+
- sources:
|
88 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
89 |
+
layer_range: [9, 10]
|
90 |
+
- sources:
|
91 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
92 |
+
layer_range: [10, 11]
|
93 |
+
- sources:
|
94 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
95 |
+
layer_range: [10, 11]
|
96 |
+
- sources:
|
97 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
98 |
+
layer_range: [11, 12]
|
99 |
+
- sources:
|
100 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
101 |
+
layer_range: [11, 12]
|
102 |
+
- sources:
|
103 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
104 |
+
layer_range: [12, 13]
|
105 |
+
- sources:
|
106 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
107 |
+
layer_range: [12, 13]
|
108 |
+
- sources:
|
109 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
110 |
+
layer_range: [13, 14]
|
111 |
+
- sources:
|
112 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
113 |
+
layer_range: [13, 14]
|
114 |
+
- sources:
|
115 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
116 |
+
layer_range: [14, 15]
|
117 |
+
- sources:
|
118 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
119 |
+
layer_range: [14, 15]
|
120 |
+
- sources:
|
121 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
122 |
+
layer_range: [15, 16]
|
123 |
+
- sources:
|
124 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
125 |
+
layer_range: [15, 16]
|
126 |
+
- sources:
|
127 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
128 |
+
layer_range: [16, 17]
|
129 |
+
- sources:
|
130 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
131 |
+
layer_range: [16, 17]
|
132 |
+
- sources:
|
133 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
134 |
+
layer_range: [17, 18]
|
135 |
+
- sources:
|
136 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
137 |
+
layer_range: [17, 18]
|
138 |
+
- sources:
|
139 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
140 |
+
layer_range: [18, 19]
|
141 |
+
- sources:
|
142 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
143 |
+
layer_range: [18, 19]
|
144 |
+
- sources:
|
145 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
146 |
+
layer_range: [19, 20]
|
147 |
+
- sources:
|
148 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
149 |
+
layer_range: [19, 20]
|
150 |
+
- sources:
|
151 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
152 |
+
layer_range: [20, 21]
|
153 |
+
- sources:
|
154 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
155 |
+
layer_range: [20, 21]
|
156 |
+
- sources:
|
157 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
158 |
+
layer_range: [21, 22]
|
159 |
+
- sources:
|
160 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
161 |
+
layer_range: [21, 22]
|
162 |
+
- sources:
|
163 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
164 |
+
layer_range: [22, 23]
|
165 |
+
- sources:
|
166 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
167 |
+
layer_range: [22, 23]
|
168 |
+
- sources:
|
169 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
170 |
+
layer_range: [23, 24]
|
171 |
+
- sources:
|
172 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
173 |
+
layer_range: [23, 24]
|
174 |
+
- sources:
|
175 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
176 |
+
layer_range: [24, 25]
|
177 |
+
- sources:
|
178 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
179 |
+
layer_range: [24, 25]
|
180 |
+
- sources:
|
181 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
182 |
+
layer_range: [25, 26]
|
183 |
+
- sources:
|
184 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
185 |
+
layer_range: [25, 26]
|
186 |
+
- sources:
|
187 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
188 |
+
layer_range: [26, 27]
|
189 |
+
- sources:
|
190 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
191 |
+
layer_range: [26, 27]
|
192 |
+
- sources:
|
193 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
194 |
+
layer_range: [27, 28]
|
195 |
+
- sources:
|
196 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
197 |
+
layer_range: [27, 28]
|
198 |
+
- sources:
|
199 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
200 |
+
layer_range: [28, 29]
|
201 |
+
- sources:
|
202 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
203 |
+
layer_range: [28, 29]
|
204 |
+
- sources:
|
205 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
206 |
+
layer_range: [29, 30]
|
207 |
+
- sources:
|
208 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
209 |
+
layer_range: [29, 30]
|
210 |
+
- sources:
|
211 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
212 |
+
layer_range: [30, 31]
|
213 |
+
- sources:
|
214 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
215 |
+
layer_range: [30, 31]
|
216 |
+
- sources:
|
217 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
218 |
+
layer_range: [31, 32]
|
219 |
+
- sources:
|
220 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
221 |
+
layer_range: [31, 32]
|
222 |
+
- sources:
|
223 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
224 |
+
layer_range: [32, 33]
|
225 |
+
- sources:
|
226 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
227 |
+
layer_range: [32, 33]
|
228 |
+
- sources:
|
229 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
230 |
+
layer_range: [33, 34]
|
231 |
+
- sources:
|
232 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
233 |
+
layer_range: [33, 34]
|
234 |
+
- sources:
|
235 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
236 |
+
layer_range: [34, 35]
|
237 |
+
- sources:
|
238 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
239 |
+
layer_range: [34, 35]
|
240 |
+
- sources:
|
241 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
242 |
+
layer_range: [35, 36]
|
243 |
+
- sources:
|
244 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
245 |
+
layer_range: [35, 36]
|
246 |
+
- sources:
|
247 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
248 |
+
layer_range: [36, 37]
|
249 |
+
- sources:
|
250 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
251 |
+
layer_range: [36, 37]
|
252 |
+
- sources:
|
253 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
254 |
+
layer_range: [37, 38]
|
255 |
+
- sources:
|
256 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
257 |
+
layer_range: [37, 38]
|
258 |
+
- sources:
|
259 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
260 |
+
layer_range: [38, 39]
|
261 |
+
- sources:
|
262 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
263 |
+
layer_range: [38, 39]
|
264 |
+
- sources:
|
265 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
266 |
+
layer_range: [39, 40]
|
267 |
+
- sources:
|
268 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
269 |
+
layer_range: [39, 40]
|
270 |
+
- sources:
|
271 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
272 |
+
layer_range: [40, 41]
|
273 |
+
- sources:
|
274 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
275 |
+
layer_range: [40, 41]
|
276 |
+
- sources:
|
277 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
278 |
+
layer_range: [41, 42]
|
279 |
+
- sources:
|
280 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
281 |
+
layer_range: [41, 42]
|
282 |
+
- sources:
|
283 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
284 |
+
layer_range: [42, 43]
|
285 |
+
- sources:
|
286 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
287 |
+
layer_range: [42, 43]
|
288 |
+
- sources:
|
289 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
290 |
+
layer_range: [43, 44]
|
291 |
+
- sources:
|
292 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
293 |
+
layer_range: [43, 44]
|
294 |
+
- sources:
|
295 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
296 |
+
layer_range: [44, 45]
|
297 |
+
- sources:
|
298 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
299 |
+
layer_range: [44, 45]
|
300 |
+
- sources:
|
301 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
302 |
+
layer_range: [45, 46]
|
303 |
+
- sources:
|
304 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
305 |
+
layer_range: [45, 46]
|
306 |
+
- sources:
|
307 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
308 |
+
layer_range: [46, 47]
|
309 |
+
- sources:
|
310 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
311 |
+
layer_range: [46, 47]
|
312 |
+
- sources:
|
313 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
314 |
+
layer_range: [47, 48]
|
315 |
+
- sources:
|
316 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
317 |
+
layer_range: [47, 48]
|
318 |
+
- sources:
|
319 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
320 |
+
layer_range: [48, 49]
|
321 |
+
- sources:
|
322 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
323 |
+
layer_range: [48, 49]
|
324 |
+
- sources:
|
325 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
326 |
+
layer_range: [49, 50]
|
327 |
+
- sources:
|
328 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
329 |
+
layer_range: [49, 50]
|
330 |
+
- sources:
|
331 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
332 |
+
layer_range: [50, 51]
|
333 |
+
- sources:
|
334 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
335 |
+
layer_range: [50, 51]
|
336 |
+
- sources:
|
337 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
338 |
+
layer_range: [51, 52]
|
339 |
+
- sources:
|
340 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
341 |
+
layer_range: [51, 52]
|
342 |
+
- sources:
|
343 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
344 |
+
layer_range: [52, 53]
|
345 |
+
- sources:
|
346 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
347 |
+
layer_range: [52, 53]
|
348 |
+
- sources:
|
349 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
350 |
+
layer_range: [53, 54]
|
351 |
+
- sources:
|
352 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
353 |
+
layer_range: [53, 54]
|
354 |
+
- sources:
|
355 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
356 |
+
layer_range: [54, 55]
|
357 |
+
- sources:
|
358 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
359 |
+
layer_range: [54, 55]
|
360 |
+
- sources:
|
361 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
362 |
+
layer_range: [55, 56]
|
363 |
+
- sources:
|
364 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
365 |
+
layer_range: [55, 56]
|
366 |
+
- sources:
|
367 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
368 |
+
layer_range: [56, 57]
|
369 |
+
- sources:
|
370 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
371 |
+
layer_range: [56, 57]
|
372 |
+
- sources:
|
373 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
374 |
+
layer_range: [57, 58]
|
375 |
+
- sources:
|
376 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
377 |
+
layer_range: [57, 58]
|
378 |
+
- sources:
|
379 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
380 |
+
layer_range: [58, 59]
|
381 |
+
- sources:
|
382 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
383 |
+
layer_range: [58, 59]
|
384 |
+
- sources:
|
385 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
386 |
+
layer_range: [59, 60]
|
387 |
+
- sources:
|
388 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
389 |
+
layer_range: [59, 60]
|
390 |
+
- sources:
|
391 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
392 |
+
layer_range: [60, 61]
|
393 |
+
- sources:
|
394 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
395 |
+
layer_range: [60, 61]
|
396 |
+
- sources:
|
397 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
398 |
+
layer_range: [61, 62]
|
399 |
+
- sources:
|
400 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
401 |
+
layer_range: [61, 62]
|
402 |
+
- sources:
|
403 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
404 |
+
layer_range: [62, 63]
|
405 |
+
- sources:
|
406 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
407 |
+
layer_range: [62, 63]
|
408 |
+
- sources:
|
409 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
410 |
+
layer_range: [63, 64]
|
411 |
+
- sources:
|
412 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
413 |
+
layer_range: [63, 64]
|
414 |
+
- sources:
|
415 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
416 |
+
layer_range: [64, 65]
|
417 |
+
- sources:
|
418 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
419 |
+
layer_range: [64, 65]
|
420 |
+
- sources:
|
421 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
422 |
+
layer_range: [65, 66]
|
423 |
+
- sources:
|
424 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
425 |
+
layer_range: [65, 66]
|
426 |
+
- sources:
|
427 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
428 |
+
layer_range: [66, 67]
|
429 |
+
- sources:
|
430 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
431 |
+
layer_range: [66, 67]
|
432 |
+
- sources:
|
433 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
434 |
+
layer_range: [67, 68]
|
435 |
+
- sources:
|
436 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
437 |
+
layer_range: [67, 68]
|
438 |
+
- sources:
|
439 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
440 |
+
layer_range: [68, 69]
|
441 |
+
- sources:
|
442 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
443 |
+
layer_range: [68, 69]
|
444 |
+
- sources:
|
445 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
446 |
+
layer_range: [69, 70]
|
447 |
+
- sources:
|
448 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
449 |
+
layer_range: [69, 70]
|
450 |
+
- sources:
|
451 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
452 |
+
layer_range: [70, 71]
|
453 |
+
- sources:
|
454 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
455 |
+
layer_range: [70, 71]
|
456 |
+
- sources:
|
457 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
458 |
+
layer_range: [71, 72]
|
459 |
+
- sources:
|
460 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
461 |
+
layer_range: [71, 72]
|
462 |
+
- sources:
|
463 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
464 |
+
layer_range: [72, 73]
|
465 |
+
- sources:
|
466 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
467 |
+
layer_range: [72, 73]
|
468 |
+
- sources:
|
469 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
470 |
+
layer_range: [73, 74]
|
471 |
+
- sources:
|
472 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
473 |
+
layer_range: [73, 74]
|
474 |
+
- sources:
|
475 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
476 |
+
layer_range: [74, 75]
|
477 |
+
- sources:
|
478 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
479 |
+
layer_range: [74, 75]
|
480 |
+
- sources:
|
481 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
482 |
+
layer_range: [75, 76]
|
483 |
+
- sources:
|
484 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
485 |
+
layer_range: [75, 76]
|
486 |
+
- sources:
|
487 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
488 |
+
layer_range: [76, 77]
|
489 |
+
- sources:
|
490 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
491 |
+
layer_range: [76, 77]
|
492 |
+
- sources:
|
493 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
494 |
+
layer_range: [77, 78]
|
495 |
+
- sources:
|
496 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
497 |
+
layer_range: [77, 78]
|
498 |
+
- sources:
|
499 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
500 |
+
layer_range: [78, 79]
|
501 |
+
- sources:
|
502 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
503 |
+
layer_range: [78, 79]
|
504 |
+
- sources:
|
505 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
506 |
+
layer_range: [79, 80]
|
507 |
+
- sources:
|
508 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
509 |
+
layer_range: [79, 80]
|
510 |
+
merge_method: passthrough
|
511 |
+
dtype: float16
|
512 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-72B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 29568,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 70,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_hidden_layers": 160,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.44.1",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 152064
|
28 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
4 |
+
layer_range: [0, 1]
|
5 |
+
- sources:
|
6 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
7 |
+
layer_range: [0, 1]
|
8 |
+
- sources:
|
9 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
10 |
+
layer_range: [1, 2]
|
11 |
+
- sources:
|
12 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
13 |
+
layer_range: [1, 2]
|
14 |
+
- sources:
|
15 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
16 |
+
layer_range: [2, 3]
|
17 |
+
- sources:
|
18 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
19 |
+
layer_range: [2, 3]
|
20 |
+
- sources:
|
21 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
22 |
+
layer_range: [3, 4]
|
23 |
+
- sources:
|
24 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
25 |
+
layer_range: [3, 4]
|
26 |
+
- sources:
|
27 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
28 |
+
layer_range: [4, 5]
|
29 |
+
- sources:
|
30 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
31 |
+
layer_range: [4, 5]
|
32 |
+
- sources:
|
33 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
34 |
+
layer_range: [5, 6]
|
35 |
+
- sources:
|
36 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
37 |
+
layer_range: [5, 6]
|
38 |
+
- sources:
|
39 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
40 |
+
layer_range: [6, 7]
|
41 |
+
- sources:
|
42 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
43 |
+
layer_range: [6, 7]
|
44 |
+
- sources:
|
45 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
46 |
+
layer_range: [7, 8]
|
47 |
+
- sources:
|
48 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
49 |
+
layer_range: [7, 8]
|
50 |
+
- sources:
|
51 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
52 |
+
layer_range: [8, 9]
|
53 |
+
- sources:
|
54 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
55 |
+
layer_range: [8, 9]
|
56 |
+
- sources:
|
57 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
58 |
+
layer_range: [9, 10]
|
59 |
+
- sources:
|
60 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
61 |
+
layer_range: [9, 10]
|
62 |
+
- sources:
|
63 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
64 |
+
layer_range: [10, 11]
|
65 |
+
- sources:
|
66 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
67 |
+
layer_range: [10, 11]
|
68 |
+
- sources:
|
69 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
70 |
+
layer_range: [11, 12]
|
71 |
+
- sources:
|
72 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
73 |
+
layer_range: [11, 12]
|
74 |
+
- sources:
|
75 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
76 |
+
layer_range: [12, 13]
|
77 |
+
- sources:
|
78 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
79 |
+
layer_range: [12, 13]
|
80 |
+
- sources:
|
81 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
82 |
+
layer_range: [13, 14]
|
83 |
+
- sources:
|
84 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
85 |
+
layer_range: [13, 14]
|
86 |
+
- sources:
|
87 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
88 |
+
layer_range: [14, 15]
|
89 |
+
- sources:
|
90 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
91 |
+
layer_range: [14, 15]
|
92 |
+
- sources:
|
93 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
94 |
+
layer_range: [15, 16]
|
95 |
+
- sources:
|
96 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
97 |
+
layer_range: [15, 16]
|
98 |
+
- sources:
|
99 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
100 |
+
layer_range: [16, 17]
|
101 |
+
- sources:
|
102 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
103 |
+
layer_range: [16, 17]
|
104 |
+
- sources:
|
105 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
106 |
+
layer_range: [17, 18]
|
107 |
+
- sources:
|
108 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
109 |
+
layer_range: [17, 18]
|
110 |
+
- sources:
|
111 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
112 |
+
layer_range: [18, 19]
|
113 |
+
- sources:
|
114 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
115 |
+
layer_range: [18, 19]
|
116 |
+
- sources:
|
117 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
118 |
+
layer_range: [19, 20]
|
119 |
+
- sources:
|
120 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
121 |
+
layer_range: [19, 20]
|
122 |
+
- sources:
|
123 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
124 |
+
layer_range: [20, 21]
|
125 |
+
- sources:
|
126 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
127 |
+
layer_range: [20, 21]
|
128 |
+
- sources:
|
129 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
130 |
+
layer_range: [21, 22]
|
131 |
+
- sources:
|
132 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
133 |
+
layer_range: [21, 22]
|
134 |
+
- sources:
|
135 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
136 |
+
layer_range: [22, 23]
|
137 |
+
- sources:
|
138 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
139 |
+
layer_range: [22, 23]
|
140 |
+
- sources:
|
141 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
142 |
+
layer_range: [23, 24]
|
143 |
+
- sources:
|
144 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
145 |
+
layer_range: [23, 24]
|
146 |
+
- sources:
|
147 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
148 |
+
layer_range: [24, 25]
|
149 |
+
- sources:
|
150 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
151 |
+
layer_range: [24, 25]
|
152 |
+
- sources:
|
153 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
154 |
+
layer_range: [25, 26]
|
155 |
+
- sources:
|
156 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
157 |
+
layer_range: [25, 26]
|
158 |
+
- sources:
|
159 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
160 |
+
layer_range: [26, 27]
|
161 |
+
- sources:
|
162 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
163 |
+
layer_range: [26, 27]
|
164 |
+
- sources:
|
165 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
166 |
+
layer_range: [27, 28]
|
167 |
+
- sources:
|
168 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
169 |
+
layer_range: [27, 28]
|
170 |
+
- sources:
|
171 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
172 |
+
layer_range: [28, 29]
|
173 |
+
- sources:
|
174 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
175 |
+
layer_range: [28, 29]
|
176 |
+
- sources:
|
177 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
178 |
+
layer_range: [29, 30]
|
179 |
+
- sources:
|
180 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
181 |
+
layer_range: [29, 30]
|
182 |
+
- sources:
|
183 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
184 |
+
layer_range: [30, 31]
|
185 |
+
- sources:
|
186 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
187 |
+
layer_range: [30, 31]
|
188 |
+
- sources:
|
189 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
190 |
+
layer_range: [31, 32]
|
191 |
+
- sources:
|
192 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
193 |
+
layer_range: [31, 32]
|
194 |
+
- sources:
|
195 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
196 |
+
layer_range: [32, 33]
|
197 |
+
- sources:
|
198 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
199 |
+
layer_range: [32, 33]
|
200 |
+
- sources:
|
201 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
202 |
+
layer_range: [33, 34]
|
203 |
+
- sources:
|
204 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
205 |
+
layer_range: [33, 34]
|
206 |
+
- sources:
|
207 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
208 |
+
layer_range: [34, 35]
|
209 |
+
- sources:
|
210 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
211 |
+
layer_range: [34, 35]
|
212 |
+
- sources:
|
213 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
214 |
+
layer_range: [35, 36]
|
215 |
+
- sources:
|
216 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
217 |
+
layer_range: [35, 36]
|
218 |
+
- sources:
|
219 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
220 |
+
layer_range: [36, 37]
|
221 |
+
- sources:
|
222 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
223 |
+
layer_range: [36, 37]
|
224 |
+
- sources:
|
225 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
226 |
+
layer_range: [37, 38]
|
227 |
+
- sources:
|
228 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
229 |
+
layer_range: [37, 38]
|
230 |
+
- sources:
|
231 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
232 |
+
layer_range: [38, 39]
|
233 |
+
- sources:
|
234 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
235 |
+
layer_range: [38, 39]
|
236 |
+
- sources:
|
237 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
238 |
+
layer_range: [39, 40]
|
239 |
+
- sources:
|
240 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
241 |
+
layer_range: [39, 40]
|
242 |
+
- sources:
|
243 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
244 |
+
layer_range: [40, 41]
|
245 |
+
- sources:
|
246 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
247 |
+
layer_range: [40, 41]
|
248 |
+
- sources:
|
249 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
250 |
+
layer_range: [41, 42]
|
251 |
+
- sources:
|
252 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
253 |
+
layer_range: [41, 42]
|
254 |
+
- sources:
|
255 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
256 |
+
layer_range: [42, 43]
|
257 |
+
- sources:
|
258 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
259 |
+
layer_range: [42, 43]
|
260 |
+
- sources:
|
261 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
262 |
+
layer_range: [43, 44]
|
263 |
+
- sources:
|
264 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
265 |
+
layer_range: [43, 44]
|
266 |
+
- sources:
|
267 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
268 |
+
layer_range: [44, 45]
|
269 |
+
- sources:
|
270 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
271 |
+
layer_range: [44, 45]
|
272 |
+
- sources:
|
273 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
274 |
+
layer_range: [45, 46]
|
275 |
+
- sources:
|
276 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
277 |
+
layer_range: [45, 46]
|
278 |
+
- sources:
|
279 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
280 |
+
layer_range: [46, 47]
|
281 |
+
- sources:
|
282 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
283 |
+
layer_range: [46, 47]
|
284 |
+
- sources:
|
285 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
286 |
+
layer_range: [47, 48]
|
287 |
+
- sources:
|
288 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
289 |
+
layer_range: [47, 48]
|
290 |
+
- sources:
|
291 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
292 |
+
layer_range: [48, 49]
|
293 |
+
- sources:
|
294 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
295 |
+
layer_range: [48, 49]
|
296 |
+
- sources:
|
297 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
298 |
+
layer_range: [49, 50]
|
299 |
+
- sources:
|
300 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
301 |
+
layer_range: [49, 50]
|
302 |
+
- sources:
|
303 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
304 |
+
layer_range: [50, 51]
|
305 |
+
- sources:
|
306 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
307 |
+
layer_range: [50, 51]
|
308 |
+
- sources:
|
309 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
310 |
+
layer_range: [51, 52]
|
311 |
+
- sources:
|
312 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
313 |
+
layer_range: [51, 52]
|
314 |
+
- sources:
|
315 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
316 |
+
layer_range: [52, 53]
|
317 |
+
- sources:
|
318 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
319 |
+
layer_range: [52, 53]
|
320 |
+
- sources:
|
321 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
322 |
+
layer_range: [53, 54]
|
323 |
+
- sources:
|
324 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
325 |
+
layer_range: [53, 54]
|
326 |
+
- sources:
|
327 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
328 |
+
layer_range: [54, 55]
|
329 |
+
- sources:
|
330 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
331 |
+
layer_range: [54, 55]
|
332 |
+
- sources:
|
333 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
334 |
+
layer_range: [55, 56]
|
335 |
+
- sources:
|
336 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
337 |
+
layer_range: [55, 56]
|
338 |
+
- sources:
|
339 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
340 |
+
layer_range: [56, 57]
|
341 |
+
- sources:
|
342 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
343 |
+
layer_range: [56, 57]
|
344 |
+
- sources:
|
345 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
346 |
+
layer_range: [57, 58]
|
347 |
+
- sources:
|
348 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
349 |
+
layer_range: [57, 58]
|
350 |
+
- sources:
|
351 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
352 |
+
layer_range: [58, 59]
|
353 |
+
- sources:
|
354 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
355 |
+
layer_range: [58, 59]
|
356 |
+
- sources:
|
357 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
358 |
+
layer_range: [59, 60]
|
359 |
+
- sources:
|
360 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
361 |
+
layer_range: [59, 60]
|
362 |
+
- sources:
|
363 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
364 |
+
layer_range: [60, 61]
|
365 |
+
- sources:
|
366 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
367 |
+
layer_range: [60, 61]
|
368 |
+
- sources:
|
369 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
370 |
+
layer_range: [61, 62]
|
371 |
+
- sources:
|
372 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
373 |
+
layer_range: [61, 62]
|
374 |
+
- sources:
|
375 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
376 |
+
layer_range: [62, 63]
|
377 |
+
- sources:
|
378 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
379 |
+
layer_range: [62, 63]
|
380 |
+
- sources:
|
381 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
382 |
+
layer_range: [63, 64]
|
383 |
+
- sources:
|
384 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
385 |
+
layer_range: [63, 64]
|
386 |
+
- sources:
|
387 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
388 |
+
layer_range: [64, 65]
|
389 |
+
- sources:
|
390 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
391 |
+
layer_range: [64, 65]
|
392 |
+
- sources:
|
393 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
394 |
+
layer_range: [65, 66]
|
395 |
+
- sources:
|
396 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
397 |
+
layer_range: [65, 66]
|
398 |
+
- sources:
|
399 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
400 |
+
layer_range: [66, 67]
|
401 |
+
- sources:
|
402 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
403 |
+
layer_range: [66, 67]
|
404 |
+
- sources:
|
405 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
406 |
+
layer_range: [67, 68]
|
407 |
+
- sources:
|
408 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
409 |
+
layer_range: [67, 68]
|
410 |
+
- sources:
|
411 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
412 |
+
layer_range: [68, 69]
|
413 |
+
- sources:
|
414 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
415 |
+
layer_range: [68, 69]
|
416 |
+
- sources:
|
417 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
418 |
+
layer_range: [69, 70]
|
419 |
+
- sources:
|
420 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
421 |
+
layer_range: [69, 70]
|
422 |
+
- sources:
|
423 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
424 |
+
layer_range: [70, 71]
|
425 |
+
- sources:
|
426 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
427 |
+
layer_range: [70, 71]
|
428 |
+
- sources:
|
429 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
430 |
+
layer_range: [71, 72]
|
431 |
+
- sources:
|
432 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
433 |
+
layer_range: [71, 72]
|
434 |
+
- sources:
|
435 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
436 |
+
layer_range: [72, 73]
|
437 |
+
- sources:
|
438 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
439 |
+
layer_range: [72, 73]
|
440 |
+
- sources:
|
441 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
442 |
+
layer_range: [73, 74]
|
443 |
+
- sources:
|
444 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
445 |
+
layer_range: [73, 74]
|
446 |
+
- sources:
|
447 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
448 |
+
layer_range: [74, 75]
|
449 |
+
- sources:
|
450 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
451 |
+
layer_range: [74, 75]
|
452 |
+
- sources:
|
453 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
454 |
+
layer_range: [75, 76]
|
455 |
+
- sources:
|
456 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
457 |
+
layer_range: [75, 76]
|
458 |
+
- sources:
|
459 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
460 |
+
layer_range: [76, 77]
|
461 |
+
- sources:
|
462 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
463 |
+
layer_range: [76, 77]
|
464 |
+
- sources:
|
465 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
466 |
+
layer_range: [77, 78]
|
467 |
+
- sources:
|
468 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
469 |
+
layer_range: [77, 78]
|
470 |
+
- sources:
|
471 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
472 |
+
layer_range: [78, 79]
|
473 |
+
- sources:
|
474 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
475 |
+
layer_range: [78, 79]
|
476 |
+
- sources:
|
477 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
478 |
+
layer_range: [79, 80]
|
479 |
+
- sources:
|
480 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
481 |
+
layer_range: [79, 80]
|
482 |
+
merge_method: passthrough
|
483 |
+
dtype: float16
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5fe2faaed0d5be7ee640e20dcb502e295af64ff7ff07a3fc5133b971126f34
|
3 |
+
size 4982866376
|
model-00002-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d0a082b5ce84c583f6b1d0296f8e1627c77fdb321069b1c37dae8fce072ee69
|
3 |
+
size 4964068376
|
model-00003-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53ed9b64d9f887929983c33972245a129bede861845bfc64c772e37b1ec31f3c
|
3 |
+
size 4997660360
|
model-00004-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6c71a848bbe6595ce55c5df6ef65dd4988bb088b8d8b3329758bb388535e686
|
3 |
+
size 4565680264
|
model-00005-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3199a2843dae4a46286b975c2c6a0466ef4e4ad587c5e54ce73f290efeae7a54
|
3 |
+
size 4964068400
|
model-00006-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecf3717922f0e5354784177da638f8d20a5ca96c0bc36c7403259ba3f0f80402
|
3 |
+
size 4915904664
|
model-00007-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2e23c6a8cce14bc4d54af924187524befce526233b9bf492fd9ca258cc4819
|
3 |
+
size 4647435976
|
model-00008-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e844cf0941eaa339fb678fd94e53ef333c9faed15dfe9638e942c3c882416af4
|
3 |
+
size 4964068392
|
model-00009-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:044d571c99a5b6e09af44a67e5f816b0a959ed5b8f45fe66422d35c277126e17
|
3 |
+
size 4599272248
|
model-00010-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13b9c52da41289bd5caa4ecf2515c4ebe9cb305888e142ee6b5c717e7bae0587
|
3 |
+
size 4964068392
|
model-00011-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b79fc94e2207921944b1711ae4dc5ab96e091dce24a42e52bb70c6bfa0a6182c
|
3 |
+
size 4997660360
|
model-00012-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f52ad3f3198307f3ee65e7e51a197d438891b54a3db5c6acebf5d96df157194
|
3 |
+
size 4565680264
|
model-00013-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b62ce01f8edf32e268e1d9fdf2fe8e00ffcd18b8df804739b2b057982e0b5ada
|
3 |
+
size 4964068400
|
model-00014-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6a85b702d9c0ec7be6a9ad14de2a8332da6ea9b1d2ceb93a25c5597fe16c2b8
|
3 |
+
size 4915904664
|
model-00015-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b88208dc2dacd9f5fe1733f8643b44b32e70fbc0146ec6bfaf92333f69af2d4
|
3 |
+
size 4647435976
|
model-00016-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0404cde605c674972ea9d86e10f3257de6f99b3b7b0741f1a033550d90ec1e1e
|
3 |
+
size 4964068392
|
model-00017-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c61ba9c380e8a46d1c5b4bd83834a2014a553bbe45f0b132fd52a16015cb0d55
|
3 |
+
size 4599272248
|
model-00018-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5fb0e70bc91100f6e5dd528771a1624c02a8bcb00972d338e4dcfbd60952cb
|
3 |
+
size 4964068392
|
model-00019-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf748236efce932eaf3b446e965169732eca6089f21990c8b2a068eeefabd3ba
|
3 |
+
size 4997660360
|
model-00020-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aae7664fc9b6525e17c4307bb4b506528560f9f9f2a84b9137ace9e4ddc0d7f
|
3 |
+
size 4565680264
|
model-00021-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ed855d33757c12b387285caf0b9d47886bd0cf8ceaa9ece2da751bcdbdb35a2
|
3 |
+
size 4964068400
|
model-00022-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f8f37ffd77c63c08b721dfdfb8cdf943ec38195b89a72892c0caeace2fcc024
|
3 |
+
size 4915904664
|
model-00023-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a780a0239d0ae6e4824e6d242a6a69402bfa5681c925742298cb2279505ac0b8
|
3 |
+
size 4647435976
|
model-00024-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ea2b5009084f0fb05371a225f4b1b10df52294bf7c86b621e89908f4bf8f305
|
3 |
+
size 4964068392
|
model-00025-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5e2ee71536bd48c39c2300f89fa87e737baf35f2c05e89031c33572199771b4
|
3 |
+
size 4599272248
|
model-00026-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:810a229b8e8972d4f1c669eda4ec4c61cf6017cd58157c719cdded7b0c8dc363
|
3 |
+
size 4964068392
|
model-00027-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8805aa32f60bcb85b4df5abbd3d13d665bde556db99f26e823972763eaf3d7e
|
3 |
+
size 4997660360
|
model-00028-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce600586de75842c80c177c2041bf56da6a7cccc81039dadd0e92e5de00b79fc
|
3 |
+
size 4565680264
|
model-00029-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9af4c181f0f5d2975bee134884d3efbd9d16187d4fdf318c978558f010097739
|
3 |
+
size 4964068400
|
model-00030-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fceb9197e7628bdedf4e1b1fc58a66e0ada79ec7437fddfdb57b2135ff2ec88
|
3 |
+
size 4915904664
|
model-00031-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:962197529f178fd1038c699333a97fb54cb85a9fbbbb3ab646db83a3d3e4fd53
|
3 |
+
size 4647435976
|
model-00032-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c28db248b257b39bb173cbed266d834dab8fb68d65cd515fc0fec9d95392c0c
|
3 |
+
size 4964068392
|
model-00033-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1362a5559495789f4b32b88f0b3cc054b8b6e876259c0b5307734ab75300a51e
|
3 |
+
size 4599272248
|
model-00034-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9c28fcdc3f2015f92936862edab2fff1649079e6c6296ee6103e504d4f01101
|
3 |
+
size 4964068384
|
model-00035-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12286be9d721f11ddde316effd6ae2a3259b0cf42b1a7fe95d43a86219fcff0a
|
3 |
+
size 4997660392
|
model-00036-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:572809049c70d7809860ebcc27a775f76387de1d998def5f90e8f34b9dfec920
|
3 |
+
size 4565680304
|
model-00037-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:066dd47952fc96ed555d7f9934cc381903e0d6f3105e2b5c9b3cf1100e0b9e41
|
3 |
+
size 4964068424
|
model-00038-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ee8f8dfd64c0a925b52a1726a7fadf7908a38708058ad01254617e52fbd513b
|
3 |
+
size 4915904704
|
model-00039-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74dfa120f8d0c6338a8f39e05275a72ecc64a1d737181ac76c7fca8d4de90ef5
|
3 |
+
size 4647436016
|
model-00040-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bcbb8dc7281bed9c080a32a25c222a2a6378367e90a22bea69e809e62658ef4
|
3 |
+
size 4964068416
|
model-00041-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dab28f5df06341b6a9bce2502847934e8ce30ed4b212e9fe8eb2c113fd1889e6
|
3 |
+
size 4599272296
|
model-00042-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89920891fd62cb2c970fa09c03389448edd455ef1418236f8eaab780e49d421b
|
3 |
+
size 4964068424
|
model-00043-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f931da95762b990e875dead49a6f2b840a3cbff0fa657a0b7e5cb24448e6d206
|
3 |
+
size 4997660392
|
model-00044-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:131379b8bf43d993eb9e3d30a1be97faff3f81c9aa9623bc11b8ec7614654d15
|
3 |
+
size 4565680304
|
model-00045-of-00060.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92cedc66937c163c8970ae4d51e8aa9de75930e2f7857e1d6734fcee415e4091
|
3 |
+
size 4964068424
|