patrickvonplaten
commited on
Commit
•
d958377
1
Parent(s):
b8089eb
correct checkpoints see: https://github.com/facebookresearch/metaseq/pull/164
Browse files- config.json +7 -5
- pytorch_model-00001-of-00002.bin +2 -2
- pytorch_model.bin.index.json +3 -1
config.json
CHANGED
@@ -1,15 +1,17 @@
|
|
1 |
{
|
|
|
2 |
"activation_dropout": 0.0,
|
3 |
"activation_function": "relu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 2,
|
9 |
-
"
|
10 |
"dropout": 0.1,
|
11 |
"eos_token_id": 2,
|
12 |
"ffn_dim": 16384,
|
|
|
13 |
"init_std": 0.02,
|
14 |
"layerdrop": 0.0,
|
15 |
"max_position_embeddings": 2048,
|
@@ -17,10 +19,10 @@
|
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
19 |
"pad_token_id": 1,
|
|
|
20 |
"torch_dtype": "float16",
|
21 |
-
"transformers_version": "4.
|
22 |
"use_cache": true,
|
23 |
"vocab_size": 50272,
|
24 |
-
"word_embed_proj_dim": 4096
|
25 |
-
"prefix": "</s>"
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_remove_final_layer_norm": false,
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "relu",
|
5 |
"architectures": [
|
6 |
+
"OPTModel"
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"bos_token_id": 2,
|
10 |
+
"do_layer_norm_before": true,
|
11 |
"dropout": 0.1,
|
12 |
"eos_token_id": 2,
|
13 |
"ffn_dim": 16384,
|
14 |
+
"hidden_size": 4096,
|
15 |
"init_std": 0.02,
|
16 |
"layerdrop": 0.0,
|
17 |
"max_position_embeddings": 2048,
|
|
|
19 |
"num_attention_heads": 32,
|
20 |
"num_hidden_layers": 32,
|
21 |
"pad_token_id": 1,
|
22 |
+
"prefix": "</s>",
|
23 |
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.21.0.dev0",
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 50272,
|
27 |
+
"word_embed_proj_dim": 4096
|
|
|
28 |
}
|
pytorch_model-00001-of-00002.bin
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 sha256:9fe9acfd39b64d2f51371afac60af02289eea8451c5e28ede2f67fec5505f50c
|
3 |
+
size 9960750957
|
pytorch_model.bin.index.json
CHANGED
@@ -1,10 +1,12 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"decoder.embed_positions.weight": "pytorch_model-00001-of-00002.bin",
|
7 |
"decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
|
|
|
|
8 |
"decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
9 |
"decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
"decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00002.bin",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 13316947968
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"decoder.embed_positions.weight": "pytorch_model-00001-of-00002.bin",
|
7 |
"decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"decoder.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
"decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00002.bin",
|
11 |
"decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
"decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00002.bin",
|