Ash

[BUG/Help] <50万条中文语料微调模型，模型推理无输出？烦请大佬指教>

3

### Is there an existing issue for this? - [ ] I have searched the existing issues ### Current Behavior 搜集了50万条的中文语料，语料的格式为：{"instruction": "输入一个数，判断它是否是质数。 \n数字: 47", "input": "", "output": "是质数。"}，如果取50万条中的前1万条进行微调，加载微调后的模型进行推理，可以得到回复，但是加载用全部数据微调的模型进行推理，却不能给出回复，请问导致这个问题的原因是什么，又该如何解决呢？ ### Expected...

After merging the Qwen model, the model failed to load due to missing files

1

Excuse me, I have a few questions to ask,and I am loking forward to your answer: I use passthrough and slerp to merge qwen14B, here is my passthrough yaml: ```yaml...

加载llama3 70B模型时， AutoTokenizer 报错

1

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction  请问如何解决 ### Expected behavior _No response_ ### System Info _No response_ ### Others...

llamafactory-cli 启动方式让人迷惑体验感差，请考虑恢复python src/... 这样的启动方式

14

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 项目更新后，发现程序启动方式变为 llamafactory-cli xxx 这样的方式，老实说这样的方式体验感很糟，不能定位到底运行了哪个文件，不如之前的python src/... 这样的方式清晰，容易定位文件，运行报错时，也容易追踪和定位。请考虑是否改回来。 ### Expected behavior _No response_ ### System Info...

请问是否会在框架内集成RLOO算法，最新的online RLHF？

4

### Reminder - [X] I have read the README and searched the existing issues. ### System Info 论文地址：https://arxiv.org/abs/2402.14740 huggingface trl 库实现地址：https://github.com/huggingface/trl/blob/main/trl/trainer/rloo_trainer.py ### Reproduction None ### Expected behavior _No response_ ###...

Could you please upgrade the trl library to the latest version?

3

I am using LLama-Factory to train long text DPO, but enabling unsloth is not supported with the latest version of the trl library. The newest trl update includes many useful...

Evolutionary Merging out of memory

4

When attempting to merge three 14B LLMs on a custom task using the mergekit-evolve method, I ran into memory overflow issues on 8 A100 GPUs, each with 80G of memory....