Comments (3)
madhavatreplit
commented on September 1, 2024
3
Hey! Thank you for sharing your numbers!
Quick sanity checks for running on GPUs after looking at the script you shared here:
- seems like we are not using the weights in bfloat16 there? You can support that with
model.to(device='cuda:0', dtype=torch.bfloat16). - we can pass in
attn_impl='triton'kwarg inAutoModelForCausalLM.from_pretrainedto use Triton Flash Attention implementation which is faster. Note that this for you would need to install the following dependancies:flash-attn==0.2.8,triton==2.0.0.dev20221202. Note that installingflash-attnsometimes is hairy, so installtorchfirst and installflash-attnafter.
Our README in the Hub also has the exact snippets to use.
Keep me posted if this doesn't work. Happy to help you out!
from replitlm.
elikoga
commented on September 1, 2024
I'm on Windows so no Triton for me :(
Don't know how bfloat16 might affect performance but I can try later
from replitlm.
madhavatreplit
commented on September 1, 2024
That should help with inference.
Closing this issue. Let me know if you run into blockers or if I can help with anything else!
from replitlm.
Related Issues (20)
- Finetuning fails with `RuntimeError: Please install flash-attn==1.0.3.post0 and triton==2.0.0.dev20221202` HOT 2
- Speed up the inference HOT 3
- Replit code can be enhanced with RLHF (Reinforcement learning from human feedback) ?
- Expected eval results on Multiple-E?
- FlashAttention2 for ReplitLM
- Using replit_lm_tokenizer locally HOT 1
- C
- Does ReplitLM support gradient checkpoints? HOT 1
- Challenge 1.1
- Challenge 1.1
- Sync
- Replit
- Challenge 1.1
- Challenge 1.1
- Challenge 1.2
- Clothes
- GPU hosted demo link broken in README
- HTML, CSS, JS
- Maachudo
- Model fails with AttributeError: 'ReplitLMTokenizer' object has no attribute 'sp_model' 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 replitlm.