Update README.md
Browse files
README.md
CHANGED
@@ -143,4 +143,83 @@ special_tokens:
|
|
143 |
pad_token: <pad>
|
144 |
```
|
145 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
146 |
</details>
|
|
|
143 |
pad_token: <pad>
|
144 |
```
|
145 |
|
146 |
+
### Mergekit Config
|
147 |
+
```yaml
|
148 |
+
dtype: bfloat16
|
149 |
+
merge_method: passthrough
|
150 |
+
|
151 |
+
slices:
|
152 |
+
# untouched intro
|
153 |
+
- sources:
|
154 |
+
- layer_range: [0, 8]
|
155 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
156 |
+
|
157 |
+
- sources:
|
158 |
+
- layer_range: [8, 12]
|
159 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
160 |
+
# 8–16 baseline
|
161 |
+
- sources:
|
162 |
+
- layer_range: [8, 16]
|
163 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
164 |
+
# 8–16 duplicate with projections nulled
|
165 |
+
- sources:
|
166 |
+
- layer_range: [8, 16]
|
167 |
+
model: mistralai/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 |
+
|
176 |
+
# 16–24 duplicate
|
177 |
+
- sources:
|
178 |
+
- layer_range: [16, 24]
|
179 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
180 |
+
parameters:
|
181 |
+
scale:
|
182 |
+
- filter: o_proj
|
183 |
+
value: 0.0
|
184 |
+
- filter: down_proj
|
185 |
+
value: 0.0
|
186 |
+
- value: 1.0
|
187 |
+
# 16–24 baseline
|
188 |
+
- sources:
|
189 |
+
- layer_range: [16, 24]
|
190 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
191 |
+
# 16–24 duplicate
|
192 |
+
- sources:
|
193 |
+
- layer_range: [16, 24]
|
194 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
195 |
+
parameters:
|
196 |
+
scale:
|
197 |
+
- filter: o_proj
|
198 |
+
value: 0.0
|
199 |
+
- filter: down_proj
|
200 |
+
value: 0.0
|
201 |
+
- value: 1.0
|
202 |
+
|
203 |
+
# 24–32 baseline
|
204 |
+
- sources:
|
205 |
+
- layer_range: [24, 32]
|
206 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
207 |
+
# 24–32 duplicate
|
208 |
+
- sources:
|
209 |
+
- layer_range: [24, 32]
|
210 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
211 |
+
parameters:
|
212 |
+
scale:
|
213 |
+
- filter: o_proj
|
214 |
+
value: 0.0
|
215 |
+
- filter: down_proj
|
216 |
+
value: 0.0
|
217 |
+
- value: 1.0
|
218 |
+
|
219 |
+
# untouched tail
|
220 |
+
- sources:
|
221 |
+
- layer_range: [32, 40]
|
222 |
+
model: mistralai/Mistral-Nemo-Base-2407
|
223 |
+
```
|
224 |
+
|
225 |
</details>
|