Asap7772 commited on
Commit
aa95c7f
·
verified ·
1 Parent(s): 6c6c709

Upload LlamaForCausalLM

Browse files
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b15e629dce1d651fa0ada487f4f4ab5d19bc7b2c0326356534987ef773480820
3
- size 4999780232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6690056c825f0516deb3159344d1c54a0317a81e1267cc82f8fcd982f4986fa6
3
+ size 4988259848
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb83492a2852fcaae00a13611dd059ea3c1cf4bd1f7b556fce0316dd27086ca
3
- size 4999813088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70dd685492975b621022b2379bae02198639c539443b7129e393874c259eac7
3
+ size 4899116440
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df509fb5679a06b07260169e88076792adc41cc5df3803d5aa88bc6ace281d1d
3
- size 4999813128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c46f2dc9afa5ee451860a56121c7e23a46e3ff0c5cf41d34b62e658051d13b
3
+ size 4999813120
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7143d0e5ae0d6eea128ca124a043fac63b60590cbe4efb351c3c444aa38f0e54
3
- size 4832007496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17003b57876eb9eeb9a38d440dcb527b3bfff458cf3e41c3469aa316e9edddef
3
+ size 4999813128
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd2d8358d0d41b73ee51cc65be0bb12232ab494fc4365a5d106572ab6af94947
3
- size 4999813120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f262274fd7d9a62ca87a91b26a14e9c57be975cc9078188ec1d33d55d3ea698c
3
+ size 4832007496
model-00006-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75203e0e542c7389f36469cb1555784f7d7907e94d223265cb2f943998af5d6f
3
- size 3612501616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ded2335ca72bdb1755e2547a55a89ed7ea04bc353d095c4de178b5f46379ef
3
+ size 3724718664
model.safetensors.index.json CHANGED
@@ -23,24 +23,24 @@
23
  "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
  "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
  "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
  "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
  "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
31
  "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
  "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
  "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
  "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
  "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
  "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
38
  "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
  "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
  "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
  "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
  "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
@@ -77,11 +77,11 @@
77
  "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
  "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
  "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
82
  "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
85
  "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
  "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
  "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
@@ -91,10 +91,10 @@
91
  "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
  "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
  "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
98
  "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
  "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
  "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
@@ -142,8 +142,8 @@
142
  "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
  "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
  "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
147
  "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
  "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
  "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
@@ -185,24 +185,24 @@
185
  "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
  "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
  "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
190
  "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
  "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
193
  "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
  "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
  "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
  "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
  "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
198
  "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
200
  "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
201
  "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
206
  "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
  "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
  "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
@@ -250,11 +250,11 @@
250
  "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
  "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
  "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
255
  "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
258
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
  "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
@@ -293,6 +293,6 @@
293
  "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
  "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
  "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
- "model.norm.weight": "model-00001-of-00006.safetensors"
297
  }
298
  }
 
23
  "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
  "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
  "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
28
  "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
  "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
31
  "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
  "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
  "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
  "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
  "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
36
  "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
38
  "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
39
  "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
44
  "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
45
  "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
46
  "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
 
77
  "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
78
  "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
79
  "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
82
  "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
85
  "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
  "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
  "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
 
91
  "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
92
  "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
93
  "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
98
  "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
99
  "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
100
  "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
 
142
  "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
143
  "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
144
  "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
147
  "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
148
  "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
149
  "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
 
185
  "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
186
  "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
187
  "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
190
  "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
191
  "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
193
  "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
194
  "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
195
  "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
196
  "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
197
  "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
198
  "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
200
  "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
201
  "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
206
  "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
207
  "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
208
  "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
 
250
  "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
251
  "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
252
  "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
255
  "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
256
  "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
258
  "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
259
  "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
260
  "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
 
293
  "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
294
  "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
295
  "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
296
+ "model.norm.weight": "model-00006-of-00006.safetensors"
297
  }
298
  }