TheBloke commited on
Commit
75dcee8
1 Parent(s): 126302f

Update for Transformers AWQ support

Browse files
Files changed (1) hide show
  1. config.json +31 -24
config.json CHANGED
@@ -1,26 +1,33 @@
1
  {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "bos_token_id": 1,
6
- "eos_token_id": 2,
7
- "hidden_act": "silu",
8
- "hidden_size": 8192,
9
- "initializer_range": 0.02,
10
- "intermediate_size": 22016,
11
- "max_position_embeddings": 16384,
12
- "model_type": "llama",
13
- "num_attention_heads": 64,
14
- "num_hidden_layers": 48,
15
- "num_key_value_heads": 8,
16
- "pretraining_tp": 1,
17
- "rms_norm_eps": 1e-05,
18
- "rope_scaling": null,
19
- "rope_theta": 1000000,
20
- "tie_word_embeddings": false,
21
- "torch_dtype": "bfloat16",
22
- "transformers_version": "4.32.0.dev0",
23
- "use_cache": true,
24
- "vocab_size": 32000,
25
- "pad_token_id": 0
 
 
 
 
 
 
 
26
  }
 
1
  {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 8192,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 22016,
11
+ "max_position_embeddings": 16384,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 64,
14
+ "num_hidden_layers": 48,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 1000000,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.32.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000,
25
+ "pad_token_id": 0,
26
+ "quantization_config": {
27
+ "quant_method": "awq",
28
+ "zero_point": true,
29
+ "group_size": 128,
30
+ "bits": 4,
31
+ "version": "gemm"
32
+ }
33
  }