Comments (3)
indeed might be better to wait with regard to the pre-tokenizer. i am not completely sure i understood the procedure for new models like say llama3 merges. but my current understanding is illustrated by this updated kaggle script.
there is also now a problem with older models: there are some models, like phi2, which need convert-hf-to-gguf.py and not convert.py. and after the new pre-tokenizer-fix, some of these will not easily work now.
i wonder why the script not simply falls back on default in such cases. my workaround is to just use an older version for such cases.
so atm we have at least 3 number of cases afaik:
- old models like phi2 ==> older convert-hf-to-gguf.py
- new bpe models like llama3 ==> newer convert-hf-to-gguf.py with complicated pre-tokenizer-handling
- others ==> convert.py
from llm-course.
in the meanwhile, there is also a fix for the pretokenizer. i have included it in this Kaggle notebook. of course you can adapt it if you wish.
from llm-course.
Sorry for the slow response, thanks a lot for opening this issue. I saw a lot of comments about issues with the tokenization in GGUF, so I don't know if it's the right time to update AutoQuant.
I like your improvements in the first notebook. Do you think I should transfer them or should I wait until the situation is fixed?
from llm-course.
Related Issues (20)
- LazyMergeKit - Tensor model.final_layernorm.weight required but not present in model ... HOT 14
- consider adding content to learn about agents HOT 2
- INST problems in mistral 7b DPO script
- Dependency Map and minimum path for each category
- Error in mergeKit
- Can I translate it into chinese? HOT 4
- lazyaxolotl runpod not running HOT 4
- error in fine tune LLM using axolotl HOT 2
- Great work. Can I translate in Tamil. HOT 2
- My Favorite Course HOT 1
- hi please tell me the approach to solve this problem HOT 1
- plz delete this issue, sorry to bother
- Error when trying to quantize GGUF. HOT 4
- RuntimeWarning in Fine-tune Llama 3 with ORPO.ipynb HOT 1
- i-Quants in AutoQuant? HOT 2
- [Feature Request] Kahneman-Tversky Optimization HOT 1
- Error when using HuggingChat Assistant HOT 3
- Article link is wrong? HOT 2
- "LLM Training: RLHF and Its Alternatives" article URL is not correct 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 llm-course.