TheBloke commited on
Commit
b0bb1ff
1 Parent(s): eb3a205

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
- "_name_or_path": "/fsx/dakota/orca/tmp_orca",
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": 28672,
12
- "max_position_embeddings": 4096,
13
- "model_type": "llama",
14
- "num_attention_heads": 64,
15
- "num_hidden_layers": 80,
16
- "num_key_value_heads": 8,
17
- "pad_token_id": 0,
18
- "pretraining_tp": 1,
19
- "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.32.0.dev0",
24
- "use_cache": true,
25
- "vocab_size": 32000
 
 
 
 
 
 
 
26
  }
 
1
  {
2
+ "_name_or_path": "/fsx/dakota/orca/tmp_orca",
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": 28672,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 80,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.32.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000,
26
+ "quantization_config": {
27
+ "quant_method": "awq",
28
+ "zero_point": true,
29
+ "group_size": 128,
30
+ "bits": 4,
31
+ "version": "gemm"
32
+ }
33
  }