TheBloke commited on
Commit
62a3271
1 Parent(s): 65bf97f

Update for Transformers AWQ support

Browse files
Files changed (1) hide show
  1. config.json +35 -28
config.json CHANGED
@@ -1,30 +1,37 @@
1
  {
2
- "_name_or_path": "vicuna-7b-v1.5-16k",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 4096,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 11008,
12
- "max_sequence_length": 16384,
13
- "max_position_embeddings": 4096,
14
- "model_type": "llama",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 32,
18
- "pad_token_id": 0,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-05,
21
- "rope_scaling": {
22
- "factor": 4.0,
23
- "type": "linear"
24
- },
25
- "tie_word_embeddings": false,
26
- "torch_dtype": "float16",
27
- "transformers_version": "4.31.0",
28
- "use_cache": true,
29
- "vocab_size": 32000
 
 
 
 
 
 
 
30
  }
 
1
  {
2
+ "_name_or_path": "vicuna-7b-v1.5-16k",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_sequence_length": 16384,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": {
22
+ "factor": 4.0,
23
+ "type": "linear"
24
+ },
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.31.0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000,
30
+ "quantization_config": {
31
+ "quant_method": "awq",
32
+ "zero_point": true,
33
+ "group_size": 128,
34
+ "bits": 4,
35
+ "version": "gemm"
36
+ }
37
  }