rojasdiego
commited on
Commit
•
184d8ab
1
Parent(s):
8e3bdf7
Upload LlamaForCausalLM
Browse files
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a26f7a8ed87ac9f9c3cb0ee5dd8cecf67d8fc10a9e01fb641621479f617abccc
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6463ef30907a8770a27f301c0fc3387076ed67c21cfa1a5ab3cae7230ea3ef0
|
3 |
size 4999802720
|
model-00003-of-00004.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:cea92457065c3cc43771bd38850db5aea667a6fb30a7ca4a3c5c4e3c1fb8697b
|
3 |
+
size 5033381704
|
model-00004-of-00004.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 sha256:5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad
|
3 |
+
size 1050673280
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
@@ -230,11 +230,11 @@
|
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
-
"model.layers.31.input_layernorm.weight": "model-
|
234 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
235 |
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
238 |
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
@@ -293,6 +293,6 @@
|
|
293 |
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
294 |
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
295 |
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
296 |
-
"model.norm.weight": "model-
|
297 |
}
|
298 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 15783682048
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
|
|
230 |
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
231 |
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
232 |
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
235 |
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
236 |
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
238 |
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
|
|
293 |
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
294 |
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
295 |
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00004.safetensors"
|
297 |
}
|
298 |
}
|