VortexHunter23/Shed-Coder-0.2
08
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151646,7 "eos_token_id": 151643,8 "hidden_act": "silu",9 "hidden_size": 5120,10 "initializer_range": 0.02,11 "intermediate_size": 13824,12 "max_position_embeddings": 131072,13 "max_window_layers": 48,14 "model_type": "qwen2",15 "num_attention_heads": 40,16 "num_hidden_layers": 48,17 "num_key_value_heads": 8,18 "pad_token_id": 151654,19 "quantization_config": {20 "bnb_4bit_compute_dtype": "bfloat16",21 "bnb_4bit_quant_type": "nf4",22 "bnb_4bit_use_double_quant": true,23 "llm_int8_enable_fp32_cpu_offload": false,24 "llm_int8_has_fp16_weight": false,25 "llm_int8_skip_modules": null,26 "llm_int8_threshold": 6.0,27 "load_in_4bit": true,28 "load_in_8bit": false,29 "quant_method": "bitsandbytes"30 },31 "rms_norm_eps": 1e-05,32 "rope_scaling": null,33 "rope_theta": 1000000.0,34 "sliding_window": null,35 "tie_word_embeddings": false,36 "torch_dtype": "bfloat16",37 "transformers_version": "4.51.3",38 "unsloth_fixed": true,39 "unsloth_version": "2025.4.7",40 "use_cache": true,41 "use_sliding_window": false,42 "vocab_size": 15206443}44 