Sanbu

It seems that the safetensors to bin converter is not working with diffuser 0.15.0.

3

When I tried to load the converted file using load_attn_procs in version 0.15.0, an error occurred. However, it worked fine when I downgraded to version 0.14.0. But even after conversion,...

[Bug]: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as `pad_token

6

### 软件环境 ```Markdown - paddlepaddle:develop - paddlepaddle-gpu: develop 11.8 - paddlenlp: lastest 4609d07a54ab97974b962b536dde7164ab15db93 ``` ### 重复问题 - [X] I have searched the existing issues ### 错误描述 ```Markdown meta-llama/Meta-Llama-3-8B-Instruct infer error...

[Bug]: llm merge_lora_params 合并后不保存 merge权重

5

### 软件环境 ```Markdown - paddlepaddle: - paddlepaddle-gpu: develop - paddlenlp: lastest 162d8d31c84f60b804a0abeee8f4f1e4b32308ef ``` ### 重复问题 - [X] I have searched the existing issues ### 错误描述 ```Markdown 使用 llm merge_lora_params.py，合并一个 QLora...

## Description ### 1. Why the change? ### 2. User API changes ### 3. Summary of the change ### 4. How to test? - [ ] N/A - [ ]...

## Description add cpu export and generate demo (llama2) ### 1. Why the change? ### 2. User API changes no ### 3. Summary of the change add cpu export and...

CPU finetune can't work

4

Hi, I have installed ipex-llm follow the docs: https://github.com/intel-analytics/ipex-llm/tree/main/python/llm/example/CPU/QLoRA-FineTuning and i meet the error ``` found intel-openmp in /root/miniconda3/envs/llm/lib/libiomp5.so The installed version of bitsandbytes was compiled without GPU support. 8-bit...

[RFC] Add PaddlePaddle docs qa bot

1

针对当前套件信息获取,官方api文档解释相关现状,思考基于 LLM 原生的飞桨知识库问答应用

天机-任务看板🤗 —— v 0.2 迭代版本

6

感谢大家对项目的参与&支持！ 让我们继续为构建一个LLM垂直领域样板努力💪 这里是一些任务，如果想要认领你可以在评论中回复对应的任务ID + 已认领，比如 `1、2 认领` 待认领任务如下：（一个任务可以多人认领） | 项目编号 | 项目内容 | 认领人 | 已完成| | --- | --- | --- | --- | | 1 | 为tianji知识库增加Qanything支持（代码存放、启动脚本、文档）https://github.com/netease-youdao/QAnything 如有代码，则放在tianji/knowledges/qanything，如果可以方便启动，直接把启动脚本放在run，按照规则取名，并将安装与运行文档放在docs...