instruction-pretrain commited on
Commit
9dc7608
1 Parent(s): 2c92c61

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +25 -26
config.json CHANGED
@@ -1,28 +1,27 @@
1
  {
2
- "_name_or_path": "hf_mirror/medicine-Llama3-8B",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
- "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 500000.0,
23
- "tie_word_embeddings": false,
24
- "torch_dtype": "float32",
25
- "transformers_version": "4.34.0",
26
- "use_cache": true,
27
- "vocab_size": 128256
28
  }
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 500000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.40.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 128256
 
27
  }