Comments (9)
感谢你的报告,我们后续会改进这里的体验。我们正在考虑优化一下小模型的切分方案,或者从根本上启动一个维护模型的进程,不用每个task都进行多次加载,释放。
from opencompass.
We recommend using English or English & Chinese for issues so that we could have broader discussion.
from opencompass.
好的 期待你们新的版本
from opencompass.
那再请问一下 我有什么设置可以加速这个模型的解码吗 目前看来八块a100要评测完一个小数据集合 还是会耗费大量的时间
from opencompass.
那再请问一下 我有什么设置可以加速这个模型的解码吗 目前看来八块a100要评测完一个小数据集合 还是会耗费大量的时间
这个一般都是模型本身以及huggingface需要考虑的问题,我们主要专注于评测部分
但是根据我们的经验,原生的llama会快于使用huggingface接口。
from opencompass.
我对huggingface解码不是特别了解 请问现在是八块卡分别加载完整的模型然后分隔数据集解码吗? 是什么导致了模型频繁开辟申请呢 batchsize的设定是否生效 因为我观测到的解码速度和我之前单卡测llama-7b的速度相差很大
from opencompass.
请问现在是八块卡分别加载完整的模型然后分隔数据集解码吗?
是的,
是什么导致了模型频繁开辟申请呢 batchsize的设定是否生效
默认的任务切分参数主要考虑的 100+B模型的推理,就是task的分片太小,导致频繁实例化,加载,推理,释放。具体可参考size 调整一下分片大小。
batchsize 是生效的,但生成慢是因为 1. GPT 这类模型,预测 N 个次,就是要推理N次,生成任务就会慢。2. huggingface 的接口会慢于原生llama,这个需要查huggingface的代码看原因。
也有可能其他的问题导致,如果有条件,可以测试一下不用opencompass纯推理同样问题所需要的开销,进行一下对比。
如果你实验的有任何改进,希望反馈给我们,我们会进一步改进opencompass的用户体验。
from opencompass.
好的感谢
from opencompass.
Feel free to re-open this issue if needed.
from opencompass.
Related Issues (20)
- [Feature] Can we find the config version that is used to produce the score displayed on leaderboard?
- [Bug] The case in Figure 11 is not in the MMBench? HOT 1
- 在进行MPT-7B模型的评测时运行[Bug]
- [Bug] checkpoint load bug HOT 4
- [Bug] Medbench dataset HOT 6
- [Bug] about cil_em_evaluator.py
- [Bug] ERROR: opencompass/tasks/openicl_eval.py - _score - 236 - Task [opt125m/siqa]: No predictions found. HOT 4
- [Bug] HOT 1
- [Bug] Error when using multiple GPUs HOT 1
- [doc] Link check failed
- [Bug] HOT 3
- [Bug] 2.0 Rankings, Hover score cannot view configuration items. HOT 1
- [Feature] 如何在此项目上测试openai接口部署的模型在数据集上的表现 HOT 1
- [Feature] Support for Multi-Turn Inference Dataset HOT 3
- [Bug] Official website ranking page, unable to view configuration items when hovering over scores with mouse HOT 2
- [Bug] 运行成功后在summary文件夹中的结果都是为空的
- 多卡推理,内存溢出[Bug]
- [Feature] Add some examples in the documentation of how to sandbox the humaneval code execution
- [Bug] CMB Dataset HOT 2
- [Feature] Why is the leaderboard called "Multi-modal Modal Leaderboard"? HOT 2
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 opencompass.