pharrow/TinyLlama-HTMLWeb-coder
021
1{
2 "architectures": [
3 "LlamaForCausalLM"
4 ],
5 "attention_bias": false,
6 "attention_dropout": 0.0,
7 "bos_token_id": 1,
8 "dtype": "float16",
9 "eos_token_id": 2,
10 "head_dim": 64,
11 "hidden_act": "silu",
12 "hidden_size": 2048,
13 "initializer_range": 0.02,
14 "intermediate_size": 5632,
15 "max_position_embeddings": 2048,
16 "mlp_bias": false,
17 "model_type": "llama",
18 "num_attention_heads": 32,
19 "num_hidden_layers": 22,
20 "num_key_value_heads": 4,
21 "pretraining_tp": 1,
22 "rms_norm_eps": 1e-05,
23 "rope_scaling": null,
24 "rope_theta": 10000.0,
25 "tie_word_embeddings": false,
26 "transformers_version": "4.56.0",
27 "use_cache": true,
28 "vocab_size": 32000
29}
30 