lvkaokao commited on
Commit
77c3182
1 Parent(s): 77439b2

update model.

Browse files
config.json CHANGED
@@ -15,6 +15,19 @@
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  "rms_norm_eps": 1e-05,
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
 
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bits": 4,
20
+ "damp_percent": 0.01,
21
+ "desc_act": false,
22
+ "group_size": 128,
23
+ "is_marlin_format": false,
24
+ "model_file_base_name": "model",
25
+ "model_name_or_path": null,
26
+ "quant_method": "gptq",
27
+ "static_groups": false,
28
+ "sym": false,
29
+ "true_sequential": false
30
+ },
31
  "rms_norm_eps": 1e-05,
32
  "rope_theta": 10000.0,
33
  "sliding_window": 4096,
autoround-model-4bit-128g.safetensors → model.safetensors RENAMED
File without changes
quantize_config.json CHANGED
@@ -7,7 +7,7 @@
7
  "sym": false,
8
  "true_sequential": false,
9
  "model_name_or_path": null,
10
- "model_file_base_name": "autoround-model-4bit-128g",
11
  "is_marlin_format": false,
12
  "quant_method": "intel/auto-round"
13
  }
 
7
  "sym": false,
8
  "true_sequential": false,
9
  "model_name_or_path": null,
10
+ "model_file_base_name": "model",
11
  "is_marlin_format": false,
12
  "quant_method": "intel/auto-round"
13
  }