Comments (9)
Luccadoremi
commented on May 24, 2024
same issue，any solution？
from qwen-vl.
ShuaiBai623
commented on May 24, 2024
如果是多卡测试，可以参考eval_mm/evaluate_caption.py 的实现来进行多卡和组batch执行
from qwen-vl.
Keep-lucky
commented on May 24, 2024
如果是多卡测试，可以参考eval_mm/evaluate_caption.py 的实现来进行多卡和组batch执行
我尝试这样做，但是使用model.generate()的方法, 生成效果远远不如model.chat()，请问model.chat()有批量推理的方法嘛？
from qwen-vl.
atomrun39
commented on May 24, 2024
如果是多卡测试，可以参考eval_mm/evaluate_caption.py 的实现来进行多卡和组batch执行
我尝试这样做，但是使用model.generate()的方法, 生成效果远远不如model.chat()，请问model.chat()有批量推理的方法嘛？
同求，请问该怎么实现啊 @ShuaiBai623
from qwen-vl.
iFe1er
commented on May 24, 2024
同样的问题 求助 @ShuaiBai623
from qwen-vl.
CrazyBrick
commented on May 24, 2024
同样的问题 求助 @ShuaiBai623
from qwen-vl.
FangGet
commented on May 24, 2024
HF上提供了一个qwen_generation_utils.py，循环调用里面make_context函数，组batch，然后调用generate函数和他提供的decode_token函数就好了
from qwen-vl.
peytoncai
commented on May 24, 2024
所以结论是qwen vl不支持多卡推理？官方没计划支持吗？
from qwen-vl.
drockser
commented on May 24, 2024
HF上提供了一个qwen_generation_utils.py，循环调用里面make_context函数，组batch，然后调用generate函数和他提供的decode_token函数就好了
这个要求 输入的query长度必须一致，如果长度不一致的话，现在好像没有合适的padding方法。
from qwen-vl.
Related Issues (20)
- Beyond被Qwen-VL-Max认为是禁止词 HOT 1
- 💡 [REQUEST] - 这次plus和max版本都没有开源，以后qwen vl是不是也不打算开源了？ HOT 2
- [BUG] <title>微调vl的全部参数出现错误 terminate called after throwing an instance of 'c10::Error' what(): CUDA error: an illegal memory access was encountered Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
- --model_max_length是输出的文本长度吗？训练时调小可以节省内存吗？
- [BUG] <title>使用Qwen-VL-Chat-Int4报错
- loss 在第二个step就变成了0 HOT 4
- [BUG] <opanai_api.py无法分析本地图片> HOT 8
- [BUG] <多样本推理，只有第一次的结果合理>
- [BUG] <使用ModelScope进行推理报错：非法指令 (核心已转储)> HOT 1
- [问题] 咨询问题，在2张4090的显卡上能不能微调训练？
- [BUG] qwen-vl 第一阶段训练loss下降后升高了，模型训崩了
- 💡 [REQUEST] - <title>怎么能够继续昨天的训练，继续训练 HOT 3
- [BUG] <title>是否支持一次Lora的基础上再次Lora HOT 1
- qwen-vl
- 请教一下，Qwen1.5的tokenizer如何上传文件。
- qwen-vl
- RuntimeError: probability tensor contains either `inf`, `nan` or element < 0 HOT 2
- 使用3000份数据全量参数微调10个epoch后依然有很大的幻觉，并且一个回答里面会重复生成 HOT 1
- 本地推理模型报错[BUG] <title>
- [BUG] <title> Qlora无法训练VL。 显示： we only spport quantization for text model. Support for vision, speech and multimodel will come later. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from qwen-vl.