| { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "unsloth/Qwen2.5-Math-7B-Instruct", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "eos_token_id": 151645, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "max_position_embeddings": 4096, |
| "max_window_layers": 28, |
| "model_type": "qwen2", |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "pad_token_id": 151665, |
| "quantization_config": { |
| "_load_in_4bit": false, |
| "_load_in_8bit": true, |
| "bnb_4bit_compute_dtype": "float32", |
| "bnb_4bit_quant_storage": "uint8", |
| "bnb_4bit_quant_type": "fp4", |
| "bnb_4bit_use_double_quant": false, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": false, |
| "load_in_8bit": true, |
| "quant_method": "bitsandbytes" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.46.0", |
| "unsloth_fixed": true, |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 152064 |
| } |
|
|
