-
Thanks for publishing this customized version of vllm.
According to the readme.md, I tried to install it and found some problems.
The error message is as follows:
```
Building wheels for collecte…
-
I am fintuning llava-internlm2 (but replacing clip with dinov2, see #297). I finish the pretraining phase successfully. But during the finetuning phase, xtuner will suddenly quits without any error re…
-
### Describe the bug
如题
### Environment
1、使用最新版1.24号更新的internlm2-chat-20b
2、使用transformers==4.36.0
3、使用vllm==0.26
4、GPU A100
### Other information
_No response_
-
### Checklist
- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.
### Describe the bug
When starting the api_…
-
### Checklist
- [x] 1. I have searched related issues but cannot get the expected help.
- [x] 2. The bug has not been fixed in the latest version.
### Describe the bug
通过 `lmdeploy lite auto_awq ` …
-
根据[readme](https://github.com/InternLM/MindSearch?tab=readme-ov-file#step2-setup-mindsearch-api),仅修改了model.py的internlm_server的模型路径为本地
```
❯ CUDA_VISIBLE_DEVICES=2 python -m mindsearch.app --lang cn …
-
### 描述该错误
微调internlm2-7b的base模型,在eval阶段使用generate时几乎每一个结果都会出现,按理说这个token是一个pad_token,他似乎不应该大量出现在generate的结果中,我不确定这是什么原因,希望您可以抽空对我的问题进行回复,感谢~
### 环境信息
python 3.10.13
transformers …
-
### 描述问题
internlm2-chat-7b通过lmdeploy能够支持200k,但是想知道本身支持的token多大?
xxg98 updated
7 months ago
-
### Checklist
- [ ] 1. I have searched related issues but cannot get the expected help.
- [ ] 2. The bug has not been fixed in the latest version.
### Describe the bug
生成的4bit模型HF格式的模型目录是 ~/lmdeplo…
-
### 提交前必须检查以下项目 | The following items must be checked before submission
- [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。 | Make sure you are using the latest code from the repository (git pull), some issue…