TheBloke commited on
Commit
c588ac3
1 Parent(s): d58f201

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
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 11008,
11
+ "max_position_embeddings": 16384,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 32,
15
+ "num_key_value_heads": 32,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.32.0",
22
+ "use_cache": true,
23
+ "vocab_size": 32016,
24
+ "auto_map": {
25
+ "AutoConfig": "configuration_llama.LlamaConfig",
26
+ "AutoModel": "modeling_llama.LlamaModel",
27
+ "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM",
28
+ "AutoModelForSequenceClassification": "modeling_llama.LlamaForSequenceClassification"
29
+ },
30
+ "rope_theta": 1000000,
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
+ }