wochaori/DeepSeek-R1-ComputerScience-COT-Qwen-7B-FineTuned
011
1{2 "_name_or_path": "unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit",3 "architectures": [4 "Qwen2ForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 151646,8 "eos_token_id": 151643,9 "hidden_act": "silu",10 "hidden_size": 3584,11 "initializer_range": 0.02,12 "intermediate_size": 18944,13 "max_position_embeddings": 131072,14 "max_window_layers": 28,15 "model_type": "qwen2",16 "num_attention_heads": 28,17 "num_hidden_layers": 28,18 "num_key_value_heads": 4,19 "pad_token_id": 151654,20 "rms_norm_eps": 1e-06,21 "rope_scaling": null,22 "rope_theta": 10000,23 "sliding_window": null,24 "tie_word_embeddings": false,25 "torch_dtype": "float16",26 "transformers_version": "4.48.3",27 "unsloth_fixed": true,28 "unsloth_version": "2025.2.4",29 "use_cache": true,30 "use_mrope": false,31 "use_sliding_window": false,32 "vocab_size": 15206433}34 