MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Merged-Lora-16bit

1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "eos_token_id": 151645,7  "hidden_act": "silu",8  "hidden_size": 3584,9  "initializer_range": 0.02,10  "intermediate_size": 18944,11  "max_position_embeddings": 32768,12  "max_window_layers": 28,13  "model_type": "qwen2",14  "num_attention_heads": 28,15  "num_hidden_layers": 28,16  "num_key_value_heads": 4,17  "pad_token_id": 151654,18  "rms_norm_eps": 1e-06,19  "rope_scaling": null,20  "rope_theta": 1000000.0,21  "sliding_window": null,22  "tie_word_embeddings": false,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.51.3",25  "unsloth_fixed": true,26  "unsloth_version": "2025.3.19",27  "use_cache": true,28  "use_sliding_window": false,29  "vocab_size": 15206430}31