TheBloke commited on
Commit
c071c96
1 Parent(s): ee74a39

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/CodeLlama-34b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 22016,
12
+ "max_position_embeddings": 16384,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 48,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.32.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000,
26
+ "auto_map": {
27
+ "AutoConfig": "configuration_llama.LlamaConfig",
28
+ "AutoModel": "modeling_llama.LlamaModel",
29
+ "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM",
30
+ "AutoModelForSequenceClassification": "modeling_llama.LlamaForSequenceClassification"
31
+ },
32
+ "rope_theta": 1000000,
33
+ "quantization_config": {
34
+ "bits": 3,
35
+ "group_size": 128,
36
+ "damp_percent": 0.1,
37
+ "desc_act": true,
38
+ "sym": true,
39
+ "true_sequential": true,
40
+ "model_name_or_path": null,
41
+ "model_file_base_name": "model",
42
+ "quant_method": "gptq"
43
+ }
44
+ }