thr3a commited on
Commit
ec6dfde
·
verified ·
1 Parent(s): 5e024dd

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +36 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_flash_attn_2_enabled": true,
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
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": 8192,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 8,
19
+ "quantization": {
20
+ "group_size": 64,
21
+ "bits": 8
22
+ },
23
+ "quantization_config": {
24
+ "group_size": 64,
25
+ "bits": 8
26
+ },
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_theta": 100000.0,
29
+ "sliding_window": 8192,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.39.3",
33
+ "use_cache": true,
34
+ "use_transformers_inputs": true,
35
+ "vocab_size": 48000
36
+ }