danielhanchen
commited on
Commit
•
d4968cc
1
Parent(s):
2544d13
Upload Qwen2ForCausalLM
Browse files
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29b03a80d00caa73c0d991ef04178ccfb7f21ef9b8fb89d765957c1cce7f4a36
|
3 |
+
size 3968650520
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a9eb9117d3c4a86e4fb446759b170cd8e1d99b97e62b6cccc59c26fc47effb9
|
3 |
+
size 2203276456
|
model.safetensors.index.json
CHANGED
@@ -172,11 +172,11 @@
|
|
172 |
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
174 |
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
-
"model.layers.21.input_layernorm.weight": "model-
|
176 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
177 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
180 |
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
181 |
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -184,90 +184,90 @@
|
|
184 |
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
186 |
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
-
"model.layers.22.input_layernorm.weight": "model-
|
188 |
-
"model.layers.22.mlp.down_proj.weight": "model-
|
189 |
-
"model.layers.22.mlp.gate_proj.weight": "model-
|
190 |
-
"model.layers.22.mlp.up_proj.weight": "model-
|
191 |
-
"model.layers.22.post_attention_layernorm.weight": "model-
|
192 |
-
"model.layers.22.self_attn.k_proj.bias": "model-
|
193 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
194 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
195 |
-
"model.layers.22.self_attn.q_proj.bias": "model-
|
196 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
197 |
-
"model.layers.22.self_attn.v_proj.bias": "model-
|
198 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
199 |
-
"model.layers.23.input_layernorm.weight": "model-
|
200 |
-
"model.layers.23.mlp.down_proj.weight": "model-
|
201 |
-
"model.layers.23.mlp.gate_proj.weight": "model-
|
202 |
-
"model.layers.23.mlp.up_proj.weight": "model-
|
203 |
-
"model.layers.23.post_attention_layernorm.weight": "model-
|
204 |
-
"model.layers.23.self_attn.k_proj.bias": "model-
|
205 |
-
"model.layers.23.self_attn.k_proj.weight": "model-
|
206 |
-
"model.layers.23.self_attn.o_proj.weight": "model-
|
207 |
-
"model.layers.23.self_attn.q_proj.bias": "model-
|
208 |
-
"model.layers.23.self_attn.q_proj.weight": "model-
|
209 |
-
"model.layers.23.self_attn.v_proj.bias": "model-
|
210 |
-
"model.layers.23.self_attn.v_proj.weight": "model-
|
211 |
-
"model.layers.24.input_layernorm.weight": "model-
|
212 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
213 |
-
"model.layers.24.mlp.gate_proj.weight": "model-
|
214 |
-
"model.layers.24.mlp.up_proj.weight": "model-
|
215 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
216 |
-
"model.layers.24.self_attn.k_proj.bias": "model-
|
217 |
-
"model.layers.24.self_attn.k_proj.weight": "model-
|
218 |
-
"model.layers.24.self_attn.o_proj.weight": "model-
|
219 |
-
"model.layers.24.self_attn.q_proj.bias": "model-
|
220 |
-
"model.layers.24.self_attn.q_proj.weight": "model-
|
221 |
-
"model.layers.24.self_attn.v_proj.bias": "model-
|
222 |
-
"model.layers.24.self_attn.v_proj.weight": "model-
|
223 |
-
"model.layers.25.input_layernorm.weight": "model-
|
224 |
-
"model.layers.25.mlp.down_proj.weight": "model-
|
225 |
-
"model.layers.25.mlp.gate_proj.weight": "model-
|
226 |
-
"model.layers.25.mlp.up_proj.weight": "model-
|
227 |
-
"model.layers.25.post_attention_layernorm.weight": "model-
|
228 |
-
"model.layers.25.self_attn.k_proj.bias": "model-
|
229 |
-
"model.layers.25.self_attn.k_proj.weight": "model-
|
230 |
-
"model.layers.25.self_attn.o_proj.weight": "model-
|
231 |
-
"model.layers.25.self_attn.q_proj.bias": "model-
|
232 |
-
"model.layers.25.self_attn.q_proj.weight": "model-
|
233 |
-
"model.layers.25.self_attn.v_proj.bias": "model-
|
234 |
-
"model.layers.25.self_attn.v_proj.weight": "model-
|
235 |
-
"model.layers.26.input_layernorm.weight": "model-
|
236 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
237 |
-
"model.layers.26.mlp.gate_proj.weight": "model-
|
238 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
239 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
240 |
-
"model.layers.26.self_attn.k_proj.bias": "model-
|
241 |
-
"model.layers.26.self_attn.k_proj.weight": "model-
|
242 |
-
"model.layers.26.self_attn.o_proj.weight": "model-
|
243 |
-
"model.layers.26.self_attn.q_proj.bias": "model-
|
244 |
-
"model.layers.26.self_attn.q_proj.weight": "model-
|
245 |
-
"model.layers.26.self_attn.v_proj.bias": "model-
|
246 |
-
"model.layers.26.self_attn.v_proj.weight": "model-
|
247 |
-
"model.layers.27.input_layernorm.weight": "model-
|
248 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
249 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
250 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
251 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
252 |
-
"model.layers.27.self_attn.k_proj.bias": "model-
|
253 |
-
"model.layers.27.self_attn.k_proj.weight": "model-
|
254 |
-
"model.layers.27.self_attn.o_proj.weight": "model-
|
255 |
-
"model.layers.27.self_attn.q_proj.bias": "model-
|
256 |
-
"model.layers.27.self_attn.q_proj.weight": "model-
|
257 |
-
"model.layers.27.self_attn.v_proj.bias": "model-
|
258 |
-
"model.layers.27.self_attn.v_proj.weight": "model-
|
259 |
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
260 |
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
261 |
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
262 |
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
263 |
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
264 |
-
"model.layers.28.self_attn.k_proj.bias": "model-
|
265 |
-
"model.layers.28.self_attn.k_proj.weight": "model-
|
266 |
-
"model.layers.28.self_attn.o_proj.weight": "model-
|
267 |
-
"model.layers.28.self_attn.q_proj.bias": "model-
|
268 |
-
"model.layers.28.self_attn.q_proj.weight": "model-
|
269 |
-
"model.layers.28.self_attn.v_proj.bias": "model-
|
270 |
-
"model.layers.28.self_attn.v_proj.weight": "model-
|
271 |
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
272 |
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
273 |
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
172 |
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
174 |
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
176 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
177 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
180 |
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
181 |
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
184 |
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
186 |
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
188 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
189 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
190 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
191 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
192 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
193 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
194 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
195 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
196 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
197 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
198 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
199 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
200 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
201 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
202 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
203 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
204 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
205 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
206 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
207 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
208 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
209 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
210 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
211 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
212 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
213 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
214 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
215 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
216 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
217 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
218 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
219 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
220 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
221 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
222 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
223 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
224 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
225 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
226 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
227 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
228 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
229 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
230 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
231 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
232 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
233 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
234 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
235 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
236 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
237 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
238 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
239 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
240 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
241 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
242 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
243 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
244 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
245 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
246 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
247 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
248 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
249 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
250 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
251 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
252 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
253 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
254 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
255 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
256 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
257 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
258 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
259 |
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
260 |
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
261 |
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
262 |
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
263 |
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
264 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
265 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
266 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
267 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
268 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
269 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
270 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
271 |
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
272 |
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
273 |
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|