patrickvonplaten commited on
Commit
90df869
1 Parent(s): ac6427b

correct checkpoints see: https://github.com/facebookresearch/metaseq/pull/164

Browse files
config.json CHANGED
@@ -1,16 +1,17 @@
1
  {
 
2
  "activation_dropout": 0.0,
3
  "activation_function": "relu",
4
  "architectures": [
5
- "OPTForCausalLM"
6
  ],
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 2,
9
- "hidden_size": 7168,
10
  "do_layer_norm_before": true,
11
  "dropout": 0.1,
12
  "eos_token_id": 2,
13
  "ffn_dim": 28672,
 
14
  "init_std": 0.02,
15
  "layerdrop": 0.0,
16
  "max_position_embeddings": 2048,
@@ -19,7 +20,7 @@
19
  "num_hidden_layers": 48,
20
  "pad_token_id": 1,
21
  "torch_dtype": "float16",
22
- "transformers_version": "4.19.0.dev0",
23
  "use_cache": true,
24
  "vocab_size": 50272,
25
  "word_embed_proj_dim": 7168
 
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": 28672,
14
+ "hidden_size": 7168,
15
  "init_std": 0.02,
16
  "layerdrop": 0.0,
17
  "max_position_embeddings": 2048,
 
20
  "num_hidden_layers": 48,
21
  "pad_token_id": 1,
22
  "torch_dtype": "float16",
23
+ "transformers_version": "4.21.0.dev0",
24
  "use_cache": true,
25
  "vocab_size": 50272,
26
  "word_embed_proj_dim": 7168
pytorch_model-00001-of-00007.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7bb10daf782ce2df3bb3afb57bc7dfa5205e9ea7e39a3987f20e395eb435106
3
- size 9794437345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a74e19aae22c2fed07717eb786104d938a0b0d97523ca7a9ca648915d544ff
3
+ size 9794466629
pytorch_model.bin.index.json CHANGED
@@ -1,10 +1,12 @@
1
  {
2
  "metadata": {
3
- "total_size": 59949051904
4
  },
5
  "weight_map": {
6
  "decoder.embed_positions.weight": "pytorch_model-00001-of-00007.bin",
7
  "decoder.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
 
 
8
  "decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00007.bin",
9
  "decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00007.bin",
10
  "decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00007.bin",
 
1
  {
2
  "metadata": {
3
+ "total_size": 59949080576
4
  },
5
  "weight_map": {
6
  "decoder.embed_positions.weight": "pytorch_model-00001-of-00007.bin",
7
  "decoder.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
8
+ "decoder.final_layer_norm.bias": "pytorch_model-00001-of-00007.bin",
9
+ "decoder.final_layer_norm.weight": "pytorch_model-00001-of-00007.bin",
10
  "decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00007.bin",
11
  "decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00007.bin",
12
  "decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00007.bin",