config.json
930 B · 41 lines · json Raw
1 {
2 "_name_or_path": "meta-llama/Llama-3.1-70B-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 "head_dim": 128,
15 "hidden_act": "silu",
16 "hidden_size": 8192,
17 "initializer_range": 0.02,
18 "intermediate_size": 28672,
19 "max_position_embeddings": 131072,
20 "mlp_bias": false,
21 "model_type": "llama",
22 "num_attention_heads": 64,
23 "num_hidden_layers": 80,
24 "num_key_value_heads": 8,
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": "4.40.0",
38 "use_cache": true,
39 "vocab_size": 128256
40 }
41