TheBloke commited on
Commit
b721cda
1 Parent(s): 13d2edb

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. config.json +42 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "auto_map": {
6
+ "AutoModelForCausalLM": "togethercomputer/LLaMA-2-7B-32K--modeling_flash_llama.LlamaForCausalLM"
7
+ },
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "type": "linear"
25
+ },
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.31.0",
29
+ "use_cache": true,
30
+ "vocab_size": 32000,
31
+ "quantization_config": {
32
+ "bits": 4,
33
+ "group_size": 128,
34
+ "damp_percent": 0.1,
35
+ "desc_act": false,
36
+ "sym": true,
37
+ "true_sequential": true,
38
+ "model_name_or_path": null,
39
+ "model_file_base_name": "model",
40
+ "quant_method": "gptq"
41
+ }
42
+ }