TheBloke commited on
Commit
59c9753
1 Parent(s): d250745

Initial GPTQ model commit

Browse files
Files changed (1) hide show
  1. config.json +46 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "llama-30b-hf/-dequantized",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 6656,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 17920,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 52,
16
+ "num_hidden_layers": 60,
17
+ "num_key_value_heads": 52,
18
+ "pad_token_id": -1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "factor": 2.0,
22
+ "type": "linear"
23
+ },
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.31.0",
27
+ "use_cache": true,
28
+ "vocab_size": 32000,
29
+ "auto_map": {
30
+ "AutoModel": "modelling_llama.LlamaModel",
31
+ "AutoModelForCausalLM": "modelling_llama.LlamaForCausalLM",
32
+ "AutoModelForSequenceClassification": "modelling_llama.LlamaForSequenceClassification"
33
+ },
34
+ "pretraining_tp": 1,
35
+ "quantization_config": {
36
+ "bits": 4,
37
+ "group_size": -1,
38
+ "damp_percent": 0.1,
39
+ "desc_act": true,
40
+ "sym": true,
41
+ "true_sequential": true,
42
+ "model_name_or_path": null,
43
+ "model_file_base_name": "model",
44
+ "quant_method": "gptq"
45
+ }
46
+ }