ThomasBaruzier commited on
Commit
add2622
·
verified ·
1 Parent(s): 13171d4

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +41 -36
config.json CHANGED
@@ -1,38 +1,43 @@
1
  {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "eos_token_id": 151645,
8
- "hidden_act": "silu",
9
- "hidden_size": 5120,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 27648,
12
- "max_position_embeddings": 32768,
13
- "max_window_layers": 64,
14
- "model_type": "qwen2",
15
- "num_attention_heads": 40,
16
- "num_hidden_layers": 64,
17
- "num_key_value_heads": 8,
18
- "rms_norm_eps": 1e-06,
19
- "rope_theta": 1000000.0,
20
- "sliding_window": 131072,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "bfloat16",
23
- "transformers_version": "4.43.1",
24
- "use_cache": true,
25
- "use_sliding_window": false,
26
- "vocab_size": 152064,
27
- "quantization_config": {
28
- "quant_method": "exl2",
29
- "version": "0.2.4",
30
- "bits": 4.7,
31
- "head_bits": 6,
32
- "calibration": {
33
- "rows": 115,
34
- "length": 2048,
35
- "dataset": "(default)"
36
- }
37
  }
38
- }
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 27648,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 64,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 0.000001,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 152064,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.2.4",
30
+ "bits": 4.7,
31
+ "head_bits": 6,
32
+ "calibration": {
33
+ "rows": 115,
34
+ "length": 2048,
35
+ "dataset": "(default)"
 
36
  }
37
+ },
38
+ "rope_scaling": {
39
+ "factor": 4.0,
40
+ "original_max_position_embeddings": 32768,
41
+ "type": "yarn"
42
+ }
43
+ }