Qwen/Qwen3-8B
2k12.7m
1{2 "architectures": [3 "Qwen3ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 151643,8 "eos_token_id": 151645,9 "head_dim": 128,10 "hidden_act": "silu",11 "hidden_size": 4096,12 "initializer_range": 0.02,13 "intermediate_size": 12288,14 "max_position_embeddings": 40960,15 "max_window_layers": 36,16 "model_type": "qwen3",17 "num_attention_heads": 32,18 "num_hidden_layers": 36,19 "num_key_value_heads": 8,20 "rms_norm_eps": 1e-06,21 "rope_scaling": null,22 "rope_theta": 1000000,23 "sliding_window": null,24 "tie_word_embeddings": false,25 "torch_dtype": "bfloat16",26 "transformers_version": "4.51.0",27 "use_cache": true,28 "use_sliding_window": false,29 "vocab_size": 15193630}