CodCodingCode/deepseek-clinical-reasoning-qwen3-8b
117
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 "layer_types": [15 "full_attention",16 "full_attention",17 "full_attention",18 "full_attention",19 "full_attention",20 "full_attention",21 "full_attention",22 "full_attention",23 "full_attention",24 "full_attention",25 "full_attention",26 "full_attention",27 "full_attention",28 "full_attention",29 "full_attention",30 "full_attention",31 "full_attention",32 "full_attention",33 "full_attention",34 "full_attention",35 "full_attention",36 "full_attention",37 "full_attention",38 "full_attention",39 "full_attention",40 "full_attention",41 "full_attention",42 "full_attention",43 "full_attention",44 "full_attention",45 "full_attention",46 "full_attention",47 "full_attention",48 "full_attention",49 "full_attention",50 "full_attention"51 ],52 "max_position_embeddings": 131072,53 "max_window_layers": 36,54 "model_type": "qwen3",55 "num_attention_heads": 32,56 "num_hidden_layers": 36,57 "num_key_value_heads": 8,58 "pad_token_id": 151645,59 "rms_norm_eps": 1e-06,60 "rope_scaling": {61 "attn_factor": 0.8782488562869419,62 "factor": 4.0,63 "original_max_position_embeddings": 32768,64 "rope_type": "yarn"65 },66 "rope_theta": 1000000,67 "sliding_window": null,68 "tie_word_embeddings": false,69 "torch_dtype": "bfloat16",70 "transformers_version": "4.53.1",71 "use_cache": true,72 "use_sliding_window": false,73 "vocab_size": 15193674}75 