{ "custom_generation_config": null, "model_params": { "model_name_or_path": "/workdir/data/models/qwen/ruadapt_qwen2.5_7B_ext_u48_part1-2_lr5e4_peft_mlp_32_32_bs128_as1.5_pv8_ft0_as1.35_kto1_as0.75_simpo2_as1.0", "generation_config": { "bos_token_id": 147075, "do_sample": true, "eos_token_id": [ 147077 ], "max_length": 32768, "max_new_tokens": 64, "pad_token_id": 147075, "stop_strings": [ "<|im_end|>" ], "temperature": 0.1, "top_k": 40, "top_p": 0.9, "transformers_version": "4.45.2", "trust_remote_code": false }, "conversation_template": { "system_prompt": "", "system_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n", "user_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n", "bot_message_template": "<|im_start|>{role}\n{content}<|im_end|>\n", "bot_message_template_incomplete": "<|im_start|>{role}\n{content}", "user_role": "user", "bot_role": "assistant", "system_role": "system", "global_prefix": "", "suffix": "<|im_start|>assistant\n", "add_special_tokens": false, "eos_token": "<|im_end|>" }, "load_in_8bit": false, "torch_dtype": "auto", "use_flash_attention_2": true, "device_map": "cuda:0", "use_fast_tokenizer": true, "leading_space": false, "space_token": null, "trust_remote_code": false, "max_model_len": 32768 }, "task_params": { "max_len": 4000, "few_shot_count": 0, "batch_size": 8, "max_sample_per_dataset": 10000000000000, "method": "calculate_tokens_proba" } }