nisten commited on
Commit
bf44c16
1 Parent(s): e55bd0b

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +3 -42
config.json CHANGED
@@ -13,6 +13,7 @@
13
  "initializer_range": 0.02,
14
  "intermediate_size": 14336,
15
  "max_position_embeddings": 8192,
 
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
18
  "num_experts": 2,
@@ -21,55 +22,15 @@
21
  "num_key_value_heads": 8,
22
  "pretraining_tp": 1,
23
  "rms_norm_eps": 1e-05,
24
- "rope_scaling": {
25
  "factor": 4.0,
26
  "original_max_position_embeddings": 8192,
27
  "type": "yarn",
28
  "finetuned": "true"
29
  },
30
- "rope_theta": 16000000.0,
31
- "router_layers": [
32
- "gate_proj",
33
- "up_proj",
34
- "down_proj"
35
- ],
36
- "router_layers_index": [
37
- 0,
38
- 1,
39
- 2,
40
- 3,
41
- 4,
42
- 5,
43
- 6,
44
- 7,
45
- 8,
46
- 9,
47
- 10,
48
- 11,
49
- 12,
50
- 13,
51
- 14,
52
- 15,
53
- 16,
54
- 17,
55
- 18,
56
- 19,
57
- 20,
58
- 21,
59
- 22,
60
- 23,
61
- 24,
62
- 25,
63
- 26,
64
- 27,
65
- 28,
66
- 29,
67
- 30,
68
- 31
69
- ],
70
  "tie_word_embeddings": false,
71
  "torch_dtype": "bfloat16",
72
- "transformers_version": "4.40.1",
73
  "use_cache": true,
74
  "vocab_size": 128256
75
  }
 
13
  "initializer_range": 0.02,
14
  "intermediate_size": 14336,
15
  "max_position_embeddings": 8192,
16
+ "max_sequence_length": 32768,
17
  "model_type": "llama",
18
  "num_attention_heads": 32,
19
  "num_experts": 2,
 
22
  "num_key_value_heads": 8,
23
  "pretraining_tp": 1,
24
  "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
  "factor": 4.0,
27
  "original_max_position_embeddings": 8192,
28
  "type": "yarn",
29
  "finetuned": "true"
30
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.40.0.dev0",
34
  "use_cache": true,
35
  "vocab_size": 128256
36
  }