Jamie@TitanML commited on
Commit
b3e0523
1 Parent(s): 19817a4

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +11 -11
config.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "_name_or_path": "TitanML/dummy_model",
3
  "architectures": [
4
  "dummy"
5
  ],
 
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
9
- "hidden_size": 8192,
10
  "initializer_range": 0.02,
11
- "intermediate_size": 28672,
12
- "max_position_embeddings": 4096,
13
  "model_type": "llama",
14
- "num_attention_heads": 64,
15
- "num_hidden_layers": 80,
16
- "num_key_value_heads": 8,
17
  "pretraining_tp": 1,
18
  "rms_norm_eps": 1e-05,
19
  "rope_scaling": null,
 
20
  "tie_word_embeddings": false,
21
- "torch_dtype": "float16",
22
- "transformers_version": "4.32.0.dev0",
23
  "use_cache": true,
24
- "vocab_size": 32000,
25
- "pad_token_id": 0
26
  }
 
1
  {
 
2
  "architectures": [
3
  "dummy"
4
  ],
5
+ "attention_bias": false,
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 5632,
12
+ "max_position_embeddings": 2048,
13
  "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 22,
16
+ "num_key_value_heads": 4,
17
  "pretraining_tp": 1,
18
  "rms_norm_eps": 1e-05,
19
  "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.35.0",
24
  "use_cache": true,
25
+ "vocab_size": 32000
 
26
  }