theprint commited on
Commit
9c0d9dc
1 Parent(s): d306db7

(Trained with Unsloth)

Browse files
Files changed (1) hide show
  1. config.json +2 -36
config.json CHANGED
@@ -1,37 +1,3 @@
1
  {
2
- "_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 131072,
15
- "mlp_bias": false,
16
- "model_type": "llama",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 32,
19
- "num_key_value_heads": 8,
20
- "pad_token_id": 128004,
21
- "pretraining_tp": 1,
22
- "rms_norm_eps": 1e-05,
23
- "rope_scaling": {
24
- "factor": 8.0,
25
- "high_freq_factor": 4.0,
26
- "low_freq_factor": 1.0,
27
- "original_max_position_embeddings": 8192,
28
- "rope_type": "llama3"
29
- },
30
- "rope_theta": 500000.0,
31
- "tie_word_embeddings": false,
32
- "torch_dtype": "bfloat16",
33
- "transformers_version": "4.44.2",
34
- "unsloth_version": "2024.8",
35
- "use_cache": true,
36
- "vocab_size": 128256
37
- }
 
1
  {
2
+ "model_type": "llama"
3
+ }