tuohai
tuohai
如果具备与 OpenAI API 的兼容性,其他应用的接入将变得无比便捷。 OpenAI API 的示例: curl https://api.openai.com/v1/audio/speech -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" -d '{ "model": "tts-1", "input": "敏捷的棕色狐狸跳过了懒狗。", "voice": "alloy" } ' --输出语音.mp3 参考文档:https://platform.openai.com/docs/api-reference/authentication
 验证集损失越来越大,准确率越来越低,能否请教一下你们的训练方法吗? 以下是我适用llama-factory的训练参数: ### model model_name_or_path: /root/autodl-tmp/Qwen2-7B-Chat ### method stage: sft do_train: true finetuning_type: lora lora_target: all pissa_init: true pissa_iter: 16 pissa_convert: true ### dataset dataset: train template: qwen cutoff_len:...