TheBloke commited on
Commit
ce5d8b4
1 Parent(s): 8098fa9

Update for Transformers AWQ support

Browse files
Files changed (1) hide show
  1. config.json +30 -23
config.json CHANGED
@@ -1,25 +1,32 @@
1
  {
2
- "_name_or_path": "upstage/llama-65b-instruct",
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": 2048,
13
- "max_sequence_length": 2048,
14
- "model_type": "llama",
15
- "num_attention_heads": 64,
16
- "num_hidden_layers": 80,
17
- "pad_token_id": 0,
18
- "rms_norm_eps": 1e-05,
19
- "tie_word_embeddings": false,
20
- "torch_dtype": "bfloat16",
21
- "transformers_version": "4.30.2",
22
- "use_cache": true,
23
- "vocab_size": 32000,
24
- "pretraining_tp": 1
 
 
 
 
 
 
 
25
  }
 
1
  {
2
+ "_name_or_path": "upstage/llama-65b-instruct",
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": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-05,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "bfloat16",
21
+ "transformers_version": "4.30.2",
22
+ "use_cache": true,
23
+ "vocab_size": 32000,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "quant_method": "awq",
27
+ "zero_point": true,
28
+ "group_size": 128,
29
+ "bits": 4,
30
+ "version": "gemm"
31
+ }
32
  }