ShoufaChen commited on
Commit
e61c6be
1 Parent(s): 4bfb360

remember json

Browse files
.gitignore CHANGED
@@ -9,8 +9,6 @@ dist
9
  # Log
10
  *.log
11
  *.log.*
12
- *.json
13
- *.jsonl
14
 
15
  # Data
16
  datasets
 
9
  # Log
10
  *.log
11
  *.log.*
 
 
12
 
13
  # Data
14
  datasets
serve/fake_json/GPT-B.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
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": 3072,
14
+ "hidden_size": 768,
15
+ "init_std": 0.02,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "opt",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "prefix": "</s>",
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.21.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 16384,
27
+ "word_embed_proj_dim": 768
28
+ }
serve/fake_json/GPT-L.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
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": 3072,
14
+ "hidden_size": 1024,
15
+ "init_std": 0.02,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "opt",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 1,
22
+ "prefix": "</s>",
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.21.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 16384,
27
+ "word_embed_proj_dim": 768
28
+ }
serve/fake_json/GPT-XL.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
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": 3072,
14
+ "hidden_size": 1280,
15
+ "init_std": 0.02,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "opt",
19
+ "num_attention_heads": 20,
20
+ "num_hidden_layers": 36,
21
+ "pad_token_id": 1,
22
+ "prefix": "</s>",
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.21.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 16384,
27
+ "word_embed_proj_dim": 768
28
+ }
serve/fake_json/GPT-XXL.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
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": 3072,
14
+ "hidden_size": 1536,
15
+ "init_std": 0.02,
16
+ "layerdrop": 0.0,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "opt",
19
+ "num_attention_heads": 24,
20
+ "num_hidden_layers": 48,
21
+ "pad_token_id": 1,
22
+ "prefix": "</s>",
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.21.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 16384,
27
+ "word_embed_proj_dim": 768
28
+ }