Comments (3)
subramen
commented on July 18, 2024
That's a good call-out, the best practice is to use the module's __call__
In this case, the change is no-op since we aren't using hooks in the model. In case you are interested in updating the code to reflect this best-practice I'd be happy to review a PR!
from llama.
mst272
commented on July 18, 2024
That's a good call-out, the best practice is to use the module's
__call__In this case, the change is no-op since we aren't using hooks in the model. In case you are interested in updating the code to reflect this best-practice I'd be happy to review a PR!
Thanks for your response.
I've submitted a PR addressing the issue based on your suggestion. Looking forward to your review!
from llama.
subramen
commented on July 18, 2024
Thanks for helping to improve the code quality @mst272, PR is merged
from llama.
Related Issues (20)
- Agnostic Atheist AI not Normal HOT 14
- Discussing a potential bias in Llama2-Chat that can lead to content safety issues
- download.sh didn't work well HOT 3
- parameter count of Llama2-70B and Llama2-13B
- Change the name of openai to closeai and change the project name to openai.
- Error: llama runner process no longer running: 3221225785
- [Generation, Question] Why does the `seed` have to be the same in different processors (`Llama.build`)?
- how can i evaluate mathematic datasets like GSM8K?
- Test Tokenizer gives Incorrect padding error
- No response from request to access models
- how to download this model HOT 1
- Providing SHA-256 hashes
- This PR will implement code for reproducing results in the following paper:
- Unable to access the Hugging Face Llama-3 model repo
- [Parallel MD5] Accelerating `download.sh`
- LLaMA3 supports an 8K token context length. When continuously pretraining with proprietary data, the majority of the text data is significantly shorter than 8K tokens, resulting in a substantial amount of padding. To enhance training efficiency and effectiveness, it is necessary to merge multiple short texts into a longer text, with the length remaining below 8K tokens. However, the question arises: how should these short texts be combined into a single training sequence? Should they be separated by delimiters, or should an approach involving masking be used during the pretraining process?
- Oddities downloading the 8b-instruct model
- How to infer answer using llama2-7b-hf?
- The instructions to install Llama3 is horrible HOT 1
- Torch Error
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 llama.