Nbenmo/MNLP_M3_mcqa_model
015
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": 1024,12 "initializer_range": 0.02,13 "intermediate_size": 3072,14 "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 ],44 "max_position_embeddings": 40960,45 "max_window_layers": 28,46 "model_type": "qwen3",47 "num_attention_heads": 16,48 "num_hidden_layers": 28,49 "num_key_value_heads": 8,50 "rms_norm_eps": 1e-06,51 "rope_scaling": null,52 "rope_theta": 1000000,53 "sliding_window": null,54 "tie_word_embeddings": true,55 "torch_dtype": "float32",56 "transformers_version": "4.53.0.dev0",57 "use_cache": true,58 "use_sliding_window": false,59 "vocab_size": 15193660}61 