TheBloke commited on
Commit
0a86edc
1 Parent(s): d5b8e5a

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": "/fsx/proj-trlx/conceptofmind/scaled-rope-private/save_model/final/yarn-llama-2-7b-3e-5-64k-400steps",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_llama.LlamaConfig",
8
+ "AutoModelForCausalLM": "modeling_llama_together_yarn.LlamaForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 11008,
16
+ "max_position_embeddings": 65536,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 32,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 16.0,
26
+ "original_max_position_embeddings": 4096,
27
+ "type": "yarn",
28
+ "finetuned": true
29
+ },
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.32.0.dev0",
33
+ "use_cache": true,
34
+ "vocab_size": 32000,
35
+ "quantization_config": {
36
+ "bits": 4,
37
+ "group_size": 128,
38
+ "damp_percent": 0.1,
39
+ "desc_act": false,
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
+ }