upload re-converted correct weights
Browse files- config.json +2 -1
- model-00001-of-00003.safetensors +0 -3
- model-00002-of-00003.safetensors +0 -3
- model-00003-of-00003.safetensors +0 -3
config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"hidden_size": 5120,
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 13824,
|
11 |
-
"max_position_embeddings":
|
12 |
"model_type": "llama",
|
13 |
"num_attention_heads": 40,
|
14 |
"num_hidden_layers": 40,
|
@@ -16,6 +16,7 @@
|
|
16 |
"pretraining_tp": 1,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
"rope_scaling": null,
|
|
|
19 |
"tie_word_embeddings": false,
|
20 |
"torch_dtype": "bfloat16",
|
21 |
"transformers_version": "4.32.0.dev0",
|
|
|
8 |
"hidden_size": 5120,
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 13824,
|
11 |
+
"max_position_embeddings": 16384,
|
12 |
"model_type": "llama",
|
13 |
"num_attention_heads": 40,
|
14 |
"num_hidden_layers": 40,
|
|
|
16 |
"pretraining_tp": 1,
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
"rope_scaling": null,
|
19 |
+
"rope_theta": 1000000,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "bfloat16",
|
22 |
"transformers_version": "4.32.0.dev0",
|
model-00001-of-00003.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:571cc7f39f5fd67e7e30c687cf47bd82080690baec8b050769b90d9ea64cd694
|
3 |
-
size 9948851872
|
|
|
|
|
|
|
|
model-00002-of-00003.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:d5db0a5ce8ccb4fe9db728f922cae6f46f4b1017325b66fec65cc5ceb0f3e7ff
|
3 |
-
size 9904123752
|
|
|
|
|
|
|
|
model-00003-of-00003.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:809cbf54388f4c8452488261792f7297722819375049f10928e8a85729a69a17
|
3 |
-
size 6179122968
|
|
|
|
|
|
|
|