memorease commited on
Commit
24683c7
·
verified ·
1 Parent(s): 5377bed

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +21 -14
config.json CHANGED
@@ -1,22 +1,29 @@
1
  {
2
- "model_type": "llama",
3
- "architectures": ["LlamaForCausalLM"],
4
- "auto_map": {
5
- "AutoConfig": "llama.LlamaConfig",
6
- "AutoModelForCausalLM": "llama.LlamaForCausalLM"
7
- },
 
 
 
8
  "hidden_size": 2048,
 
9
  "intermediate_size": 5632,
10
  "max_position_embeddings": 2048,
 
 
11
  "num_attention_heads": 32,
12
  "num_hidden_layers": 22,
13
- "vocab_size": 32000,
14
- "bos_token_id": 1,
15
- "eos_token_id": 2,
16
- "pad_token_id": 0,
17
- "torch_dtype": "float16",
18
  "rms_norm_eps": 1e-05,
19
- "use_cache": true,
 
20
  "tie_word_embeddings": false,
21
- "transformers_version": "4.35.2"
22
- }
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
  "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
  "intermediate_size": 5632,
14
  "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
  "num_attention_heads": 32,
18
  "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "pretraining_tp": 1,
 
 
 
21
  "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
  "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }