Hack337/ChatGPT-5
2337k
1{
2 "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
3 "architectures": [
4 "Qwen2ForCausalLM"
5 ],
6 "attention_dropout": 0.0,
7 "bos_token_id": 151643,
8 "eos_token_id": 151645,
9 "hidden_act": "silu",
10 "hidden_size": 896,
11 "initializer_range": 0.02,
12 "intermediate_size": 4864,
13 "max_position_embeddings": 32768,
14 "max_window_layers": 21,
15 "model_type": "qwen2",
16 "num_attention_heads": 14,
17 "num_hidden_layers": 24,
18 "num_key_value_heads": 2,
19 "rms_norm_eps": 1e-06,
20 "rope_theta": 1000000.0,
21 "sliding_window": null,
22 "tie_word_embeddings": true,
23 "torch_dtype": "float16",
24 "transformers_version": "4.43.3",
25 "use_cache": true,
26 "use_sliding_window": false,
27 "vocab_size": 151936
28}
29 