-
`commit` https://github.com/PaddlePaddle/Paddle/commit/bff34fb14dd9d9111bfcbc2f523a403b6a589d2a
**⚠️提示⚠️** `python/paddle/distributed` 模块难度稍高,可先认领其他模块任务 🤟🤟🤟
#### 🔚 第 1 批 🎉
|…
-
rtx-4090多卡推理(模型为qlora微调后qwen72b)是否支持?通过FSDP+QLoRA,可以正常对qwen-72b的模型进行微调,想问一下,如何使用rxt-4090对其进行推理部署呢?
我尝试使用如下的脚本进行多卡推理:
```
CUDA_VISIBLE_DEVICES=4,5,6,7 accelerate launch --config_file fsdp_config.y…
-
您好,关于deepke-llm,由于我的显存配置不够,我想通过使用量化的llama模型来运行这个项目,目前不考虑性能损失,只想看一下运行效果,请问我应该使用哪一版的llama量化模型才能顺利运行该项目,您能否推荐一款模型,其次,我想问,要使用量化后的llama模型,我还需要在原项目基础上做出哪些修改,非常感谢您的指导,你们的工作非常有价值,对我帮助很大,谢谢你们!
-
WARNING:root:cannot import name 'layers' from 'parl' (G:\anaconda\envs\paddle_slim\lib\site-packages\parl\__init__.py)
G:\anaconda\envs\paddle_slim\lib\site-packages\_distutils_hack\__init__.py:33:…
-
## 🐛 Bug
mlc-llm has a problem with generating text that are completely unrelated to the prompts on some models, I think this mainly affects the new models that are available with the last [tvm bug…
-
## 🐛 Bug TVM ERROR when convert_weight
llava model convert_weight failed, especially when quantization by tvm
## To Reproduce
Steps to reproduce the behavior:
```
(mlc) # mlc_llm conve…
-
I am trying to run this variant peptide detection pipeline.
It worked without any error when i ran this pipeline within 2 proteome file.
But, when i ran this pipeline with 4 mzml files, pipeline sto…
-
Bonjour,
Cela fait un moment que j'utilise votre solution avec mon capteur TIC USB, je recontre 2 problemes :
- L'intégration me detecte 2 appareils Linky un est vide et l'autre contient les r…
-
### Your current environment
N/A
### 🐛 Describe the bug
Loading without specifying `--quantization exl2` tries to load the model with quantisation mode `None`. Manually specifying that it is an e…
-
### System Info / 系統信息
Cuda 11.8
transformers 4.41.1
Python 3.12.3
Ubuntu 20.04.6 LTS
**triton 2.2.0**
### Who can help? / 谁可以帮助到您?
_No response_
### Information / 问题信息
- [X] The official ex…