danielv835 commited on
Commit
7f82b43
1 Parent(s): 71ae510

Upload OPTForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +32 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/DeepSpeedExamples/applications/DeepSpeed-Chat/output/actor-models/",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "end_token_id": 2,
15
+ "eos_token_id": 2,
16
+ "ffn_dim": 10240,
17
+ "hidden_size": 2560,
18
+ "init_std": 0.02,
19
+ "layer_norm_elementwise_affine": true,
20
+ "layerdrop": 0.0,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "opt",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "pad_token_id": 2,
26
+ "prefix": "</s>",
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.30.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 50272,
31
+ "word_embed_proj_dim": 2560
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.30.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fc693b5f060f1902323b343705e45be262f28382c0d9824656051fbfa112cd
3
+ size 5303362745