Comments (9)
Hi. The test_speedup.py only supports the testing on GPU currently. Have you tested this script on GPU?
from llm-pruner.
Hi. We update the test_speedup.py to support the testing on CPU.
Please let me know if the bug still exists with the current version.
from llm-pruner.
Are there official FLOPs statistics on LLaMa-7B and its pruned version?
from llm-pruner.
The FLOPs of the base model and the pruned model are:
from llm-pruner.
here #MACs is equivalent to #FLOPs right? I just thought that they could be two different things.
from llm-pruner.
here #MACs is equivalent to #FLOPs right? I just thought that they could be two different things.
The results presented in the table is MACs rather than FLOPs and we didn't calculated the exact FLOPs
of the model (roughly 2 times of MACs). To prevent any potential confusion, we chose not to use the term FLOPs
in our paper, and thus all the results are MACs and not equivalent to FLOPs.
from llm-pruner.
Hi. The test_speedup.py only supports the testing on GPU currently. Have you tested this script on GPU?
Hi thanks for reply! Actually I was using GPU to run this code before.
Now I've tried the new version, when ran on CPU it worked fine. But if ran on GPU, the same error still existed.
from llm-pruner.
Hi. The test_speedup.py only supports the testing on GPU currently. Have you tested this script on GPU?
Hi thanks for reply! Actually I was using GPU to run this code before.
Now I've tried the new version, when ran on CPU it worked fine. But if ran on GPU, the same error still existed.
Hi. I updated the code and fixed a bug that might cause this issue. You can give it another try, and if it still doesn't work, could you please provide your runtime environment?
from llm-pruner.
Thanks for rapid reply! I've also made the same corrections following your code for the CPU implementations, and it works now. Thanks again!
from llm-pruner.
Related Issues (20)
- 为什么num_examples默认是10? HOT 2
- Question related to the model tuning HOT 2
- Pruning MQA?
- 在将部分层进行剪枝之后,不能直接通过tgi加载模型
- Adding a tutorial for adapting new models?
- 401 Client Error: Unauthorized for url: https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer_config.json HOT 1
- cannot import name 'SiLUActivation' from 'transformers.activations' HOT 1
- Issue: Missing Generation of `pytorch_model.bin` File During Model Tuning HOT 3
- Cannot use huggface to load
- OSError: Can't load tokenizer for 'baffo32/decapoda-research-llama-7B-hf'. HOT 1
- ConnectionError: Couldn't reach https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.train.txt (ReadTimeout(ReadTimeoutError("HTTPSConnectionPool(host='raw.githubusercontent.com', port=443): Read timed out. (read timeout=100)"))) HOT 1
- The quantization of the compressed models
- 延迟评估 HOT 1
- 剪枝率值的问题
- Unable to reproduce the results for param_first and param_second in the paper after finetuning.
- RecursionError: maximum recursion depth exceeded HOT 1
- Is this method implementable on multi-GPUs?
- How to prune the embedding and lm_head?
- I tired Mistral 7b model, but I got this issue
- Pruning llama3
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 llm-pruner.