Nevil9 commited on
Commit
e6fe2af
1 Parent(s): 03b7ee7

add new config

Browse files
Files changed (1) hide show
  1. config.json +38 -9
config.json CHANGED
@@ -1,12 +1,41 @@
1
  {
2
- "model_type": "llama",
3
- "architectures": ["LLaMAForCausalLM"],
 
 
 
 
 
 
 
 
 
 
 
4
  "hidden_size": 4096,
5
- "num_hidden_layers": 32,
 
 
 
 
6
  "num_attention_heads": 32,
7
- "intermediate_size": 8192,
8
- "max_position_embeddings": 512,
9
- "vocab_size": 50265,
10
- "padding_idx": 0,
11
- "layer_norm_eps": 1e-5
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
  "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
  "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 128004,
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": "4.44.2",
38
+ "unsloth_version": "2024.9",
39
+ "use_cache": true,
40
+ "vocab_size": 128256
41
+ }