Cola Chan

Results 9 issues of Cola Chan

As it said in the origin paper: "Token Shift allows the model to learn how much new versus old information should be allocated per time step to each channel of...

yuhaogege、zhikaigege tql

Hi, congrats for your excellent work! It helps me a lot! However, i have a few Q about the dataset architecture of this repository: 1. is ChatProtect/test/test the MainTestSet in...

### 提交前必须检查以下项目 - [X] 请确保使用的是仓库最新代码(git pull),一些问题已被解决和修复。 - [X] 由于相关依赖频繁更新,请确保按照[Wiki](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki)中的相关步骤执行 - [X] 我已阅读[FAQ章节](https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki/常见问题)并且已在Issue中对问题进行了搜索,没有找到相似问题和解决方案 - [X] 第三方插件问题:例如[llama.cpp](https://github.com/ggerganov/llama.cpp)、[text-generation-webui](https://github.com/oobabooga/text-generation-webui)、[LlamaChat](https://github.com/alexrozanski/LlamaChat)等,同时建议到对应的项目中查找解决方案 - [X] 模型正确性检查:务必检查模型的[SHA256.md](https://github.com/ymcui/Chinese-LLaMA-Alpaca/blob/main/SHA256.md),模型不对的情况下无法保证效果和正常运行 ### 问题类型 下载问题 ### 基础模型 Alpaca-33B ### 操作系统 Linux ### 详细描述问题 ```...

stale

### Description of the bug: The `response.text` quick accessor only works when the response contains a valid `Part`, but none was returned. Check the `candidate.safety_ratings` to see if the response...

type:bug
status:awaiting user response
component:python sdk
status:stale

### Reminder - [x] I have read the above rules and searched the existing issues. ### System Info DPO训完Qwen2.5-7B后我的存储路径下 -rw-rw-rw- 1 root root 605 5月 14 23:35 added_tokens.json -rw-rw-rw- 1...

bug
pending

Traceback (most recent call last): File "verl/verl/trainer/main_ppo.py", line 63, in main run_ppo(config) File "verl/verl/trainer/main_ppo.py", line 80, in run_ppo ray.get(runner.run.remote(config)) File "public/verl_env/verl_env/lib/python3.10/site-packages/ray/_private/auto_init_hook.py", line 21, in auto_init_wrapper return fn(*args, **kwargs) File "/verl_env/verl_env/lib/python3.10/site-packages/ray/_private/client_mode_hook.py",...