yimo0213/CSC2516A10
019
1{
2 "architectures": [
3 "LlamaForCausalLM"
4 ],
5 "attention_bias": false,
6 "attention_dropout": 0.0,
7 "bos_token_id": 0,
8 "dtype": "float32",
9 "eos_token_id": 0,
10 "head_dim": 64,
11 "hidden_act": "silu",
12 "hidden_size": 576,
13 "initializer_range": 0.041666666666666664,
14 "intermediate_size": 1536,
15 "is_llama_config": true,
16 "max_position_embeddings": 8192,
17 "mlp_bias": false,
18 "model_type": "llama",
19 "num_attention_heads": 9,
20 "num_hidden_layers": 30,
21 "num_key_value_heads": 3,
22 "pretraining_tp": 1,
23 "rms_norm_eps": 1e-05,
24 "rope_interleaved": false,
25 "rope_scaling": null,
26 "rope_theta": 100000,
27 "tie_word_embeddings": true,
28 "transformers_version": "4.57.1",
29 "use_cache": true,
30 "vocab_size": 49152
31}
32 