wejoncy commited on
Commit
e702c14
1 Parent(s): 6fe1c93

update config

Browse files
Files changed (1) hide show
  1. config.json +19 -18
config.json CHANGED
@@ -23,7 +23,21 @@
23
  "num_hidden_layers": 80,
24
  "num_key_value_heads": 8,
25
  "pretraining_tp": 1,
26
- "quant_config": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "model.layers.0.mlp.down_proj": {
28
  "bias": null,
29
  "enable_norm": true,
@@ -13463,20 +13477,7 @@
13463
  -1,
13464
  16
13465
  ]
13466
- }
13467
- },
13468
- "rms_norm_eps": 1e-05,
13469
- "rope_scaling": {
13470
- "factor": 8.0,
13471
- "high_freq_factor": 4.0,
13472
- "low_freq_factor": 1.0,
13473
- "original_max_position_embeddings": 8192,
13474
- "rope_type": "llama3"
13475
- },
13476
- "rope_theta": 500000.0,
13477
- "tie_word_embeddings": false,
13478
- "torch_dtype": "bfloat16",
13479
- "transformers_version": "4.45.2",
13480
- "use_cache": true,
13481
- "vocab_size": 128256
13482
- }
 
23
  "num_hidden_layers": 80,
24
  "num_key_value_heads": 8,
25
  "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128256,
40
+ "quantization_config": {
41
  "model.layers.0.mlp.down_proj": {
42
  "bias": null,
43
  "enable_norm": true,
 
13477
  -1,
13478
  16
13479
  ]
13480
+ },
13481
+ "quant_method": "vptq"
13482
+ }
13483
+ }