Comments (2)
CodeCreator
commented on August 12, 2024
Thanks! I've clarified the installation instructions in the README. The general outline is to clone the repo, install dependencies and run the example inference code in the README. Unfortunately, the Llama code requires flash-attention (and there seems to be a performance gap when training the model with flash-attention and running inference without it). The OPT AutoCompressor does not use flash attention by default.
from autocompressors.
CodeCreator
commented on August 12, 2024
Closing this to due to inactivity -- feel free to re-open!
from autocompressors.
Related Issues (20)
- Inquiry for the release date of the pre-trained model HOT 1
- Question on the preprocessed data HOT 3
- CUDA out of memory. HOT 3
- Summary Vector Failures and Incomplete Answers with Numerical Contexts HOT 4
- BUG REPORT HOT 1
- Finetuning an autocompressor model HOT 4
- AttributeError: 'SubstepTrainer' object has no attribute 'do_grad_scaling' HOT 3
- Dimension of last_hidden_state size HOT 2
- RuntimeError: FlashAttention only support fp16 and bf16 data type HOT 3
- Held-out perplexity question HOT 3
- question about `position_ids` HOT 2
- Reduce the number of summary vectors HOT 2
- Question about the data preprocessing HOT 1
- Inquire on data of Table 1 HOT 1
- Some issue about ICL Experience HOT 3
- Install as python package? HOT 1
- substep & segment HOT 1
- torchrun error when generating training split HOT 3
- Your shared model trained on LLAMA2 is not trained on Lora, It's full-finetuned 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 autocompressors.