fireyanci comments

Results 13 comments of


                                            fireyanci

Using llama3 through lit lama

> While this repository is only focused on the first Llama model to keep the code as simple and readable as possible, we have the [LitGPT repository](https://github.com/Lightning-AI/litgpt) (which is an...

Using llama3 through lit lama

how to pretrain llama2?

You can read the tutorials

Resolve output characters garbled

It can understand my question and provide corresponding output, but there are some characters whose output is in garbled form

Resolve output characters garbled

Thank you very much for your reply

Resolve output characters garbled

Because I've been too busy lately, I've only started trying this method now. I can output those garbled characters from the terminal, and I'm not sure if this is related...

prompt_style

because i want use Multi round conversation data

prompt_style

Thank you very much for your reply，I've read your explanation about Dora, it's excellent. Thank you.I hope to use it in the LitGPT project.

Can this methodology be applied to closed-source large-scale models such as chatgpt?

When I followed the steps to reproduce the results and then went to evaluate_toxicity.py, I encountered an error that displayed | ERROR | __main__::129 - An error has been caught...

[BUG] 简洁阐述问题 / 问题1：IndexError: list index out of range 原因是代码尝试访问 d.choices[0].delta.content 时，choices 列表为空，导致索引超出范围。可能是 API 返回的 d 对象不符合预期结构。问题2：AttributeError: 'IndexError' object has no attribute 'body' 在异常处理中，代码尝试访问 IndexError 异常的 body 属性，但 IndexError 对象没有这个属性，因此触发了二次异常。

@Yu-YuZhang 解决了嘛，我也遇到了这个问题，当我通过oneapi 调用openai 在线大模型时会出现这种问题，若调用Qwen系列模型无此问题，请问有解决方法吗，例：gpt-3.5-turbo 在对话时会出现index error问题，在知识库对话时无此问题。