vaibhavad commited on
Commit
a4cbc92
1 Parent(s): c971a26

Create config.json

Browse files
Files changed (1) hide show
  1. config.json +42 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaEncoderModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoModel": "McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp--modeling_llama_encoder.LlamaEncoderModel"
10
+ },
11
+ "bos_token_id": 128000,
12
+ "eos_token_id": [
13
+ 128001,
14
+ 128008,
15
+ 128009
16
+ ],
17
+ "hidden_act": "silu",
18
+ "hidden_size": 4096,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 14336,
21
+ "max_position_embeddings": 131072,
22
+ "mlp_bias": false,
23
+ "model_type": "llama",
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 32,
26
+ "num_key_value_heads": 8,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": {
30
+ "factor": 8.0,
31
+ "low_freq_factor": 1.0,
32
+ "high_freq_factor": 4.0,
33
+ "original_max_position_embeddings": 8192,
34
+ "rope_type": "llama3"
35
+ },
36
+ "rope_theta": 500000.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.42.3",
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
+ }