OpeoluwaAdekoya commited on
Commit
b6338af
1 Parent(s): 2538bdb

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +42 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "MistralForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50256,
9
+ "eos_token_id": 50256,
10
+ "gradient_checkpointing": true,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "max_position_embeddings": 1024,
17
+ "model_type": "mistral",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 50256,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "bits": 4,
25
+ "damp_percent": 0.1,
26
+ "desc_act": true,
27
+ "group_size": 128,
28
+ "model_file_base_name": "model",
29
+ "model_name_or_path": null,
30
+ "quant_method": "gptq",
31
+ "sym": true,
32
+ "true_sequential": true
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_theta": 10000.0,
36
+ "sliding_window": 4096,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.42.0.dev0",
40
+ "use_cache": false,
41
+ "vocab_size": 32000
42
+ }