Comments (6)
Closing this issue, as I tried loading CodeGen-16B in mixed precision and it fits under 40GB of RAM
from bigcode-evaluation-harness.
This is not going to be full solution. I have gotten Codegen-16B-multi to work on an A6000/48GB. The script we used to pull it off is here:
https://github.com/nuprl/MultiPL-E/blob/main/inference/codegen.py
Note the crazy code for the stopping criteria. IIRC it was necessary to get things to work.
from bigcode-evaluation-harness.
Can you make sure that FP16 is set and follow memory consumption up until accelerator.prepare
?
from bigcode-evaluation-harness.
@loubnabnl I set fp16 in the accelerate launch --mixed_precision fp16
but it doesn't help. There is no GPU memory consumption up to accelerator.prepare
.
from bigcode-evaluation-harness.
@Godofnothing we found a bug which made the memory consumption more than necessary, can you try running evaluation with code from this PR #61? you now need to specify --precision fp16
from bigcode-evaluation-harness.
Sorry for long delay. I've pulled the latest version of the code and model successfully fits onto 40GB. Thanks for your help and response.
from bigcode-evaluation-harness.
Related Issues (20)
- What does 'bs' in LANGUAGES list mean?
- Support `Salesforce/codet5p-220m` and other `T5ForConditionalGeneration` models HOT 1
- how to use --instruction_tokens? HOT 1
- error: list index out of range, when testing in multi-gpu? HOT 6
- MBPP eval extremely slow for CodeGen2 and Replit-Code HOT 4
- When I evaluated the dataset APPS, I got the error RuntimeError: stack.size() >= frames.back().function->n_inputs INTERNAL ASSERT FAILED
- Reproduction of HELM results HOT 1
- Update MultiPL-E docker image
- installation issue with pip install git+https://github.com/bigcode-project/bigcode-evaluation-harness.git HOT 2
- Different stop words between humaneval and instruct humaneval HOT 1
- bug in post processing for mbpp task HOT 3
- ModuleNotFoundError: No module named 'lm_eval.ds' HOT 2
- Reproducing the performance of HumanEval on starcoder HOT 4
- santacoder fp16 causes NaN on humaneval? HOT 1
- Publish the Docker images to ghcr.io? HOT 3
- Support `transformers.pipeline(model=...)` models like `HuggingFaceH4/starchat-beta` HOT 2
- 8-bit models unsupported HOT 4
- APPS dataset prompting seems wrong HOT 1
- Getting Zeros for StarCoder on multiple-js HOT 5
- failed evaluation on GSM8K HOT 4
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 bigcode-evaluation-harness.