Hugging Face's logo

Open Source AI Research Community

community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

jending12  new activity 15 days ago
OSAIResearchCommunity/README:Update README.md
burtenshaw  updated a Space 16 days ago
OSAIResearchCommunity/README
burtenshaw  new activity 16 days ago
OSAIResearchCommunity/README:Update README.md
View all activity

OSAIResearchCommunity's activity

burtenshaw 
posted an update 7 days ago
view post
Post
2547
People are flexing their end of year stats, so I made this app to show hub stats in a tidy design!

Thanks @Ameeeee and @jfcalvo for the feature from Argilla!
burtenshaw/recap
  • 1 reply
·
jending12 
in OSAIResearchCommunity/README 15 days ago

Update README.md

1
#1 opened 16 days ago by
burtenshaw
burtenshaw 
updated a Space 16 days ago
burtenshaw 
in OSAIResearchCommunity/README 16 days ago

Update README.md

1
#1 opened 16 days ago by
burtenshaw
burtenshaw 
posted an update 16 days ago
view post
Post
2387
Quick update from week 1 of smol course. The community is taking the driving seat and using the material for their own projects. If you want to do the same, join in!

- we have ongoing translation projects in Korean, Vietnamese, Portuguese, and Spanish
- 3 chapters are ready for students. On topics like, instruction tuning, preference alignment, and parameter efficient fine tuning
- 3 chapters are in progress on evaluation, vision language models, and synthetic data.
- around 780 people have forked the repo to use it for learning, teaching, sharing.

⏭️ Next step is to support people that want to use the course for teaching, content creation, internal knowledge sharing, or anything. If you're into this. Drop an issue or PR

REPO: https://buff.ly/3ZCMKX2
discord channel: https://buff.ly/4f9F8jA
burtenshaw 
posted an update 23 days ago
view post
Post
2568
For anyone looking to boost their LLM fine-tuning and alignment skills this decemeber. We're running this free and open course called smol course. It’s not big like Li Yin and @mlabonne , it’s just smol.

👷 It focuses on practical use cases, so if you’re working on something, bring it along.

👯‍♀️ It’s peer reviewed and open so you can discuss and get feedback.

🤘 If you’re already a smol pro, feel free to drop a star or issue.

> > Part 1 starts now, and it’s on instruction tuning!

https://github.com/huggingface/smol-course
burtenshaw 
posted an update 26 days ago
view post
Post
1586
[SATURDAY ROUNDUP] ☕️🧑‍🎓

In case you missed everything this week. It’s all about vision language models and image preference datasets. Here are the models and datasets you can use in your projects.

QWQ-32B-Preview is the first open weights model to reason like o1 with comparable performance. It’s large but is acing some of the hardest tasks.

https://bsky.app/profile/philschmid.bsky.social/post/3lbylz6nzqk25

SmolVLM is a vision implementation of the recently released SmolLM2. It uses the Idefics3 approach to add a vision encoder. The main difference being the smaller language model (8b > 1.7b) and more compression of images. This results in a model that is very accurate for its memory footprint.

https://huggingface.co./blog/smolvlm

ColSmolVLM is a vision embedding model based on SmolVLM using the Colbert approach from ColPali. This is shown to be great at document retrieval and everyone should test it out in their RAG setups.

https://huggingface.co./posts/merve/663466156074132

In an effort to build a FLUX level open source image generation model, the community is building a dataset of image preferences. The dataset is already open and the project is still running. Join in!

https://huggingface.co./posts/davidberenstein1957/405018978675827

TRL tutorial Drop - This week I dropped a load of tutorials on finetuning and aligning models with TRL. If you’re upskilling in this space, you should check these out.

https://bsky.app/profile/benburtenshaw.bsky.social/post/3lbrc56ap3222
jending12 
updated a Space 26 days ago
jending12 
authored 6 papers 4 months ago
cosborne 
authored 3 papers 4 months ago
burtenshaw 
posted an update 5 months ago
view post
Post
1450
SFT + Quantisation + Unsloth is a super easy way of squeezing extra performance out of an LLM at low latencies. Here are some hand y resources to bootstrap your projects.

Here's a filtered dataset from Helpsteer2 with the most correct and coherent samples: burtenshaw/helpsteer-2-plus
This is a SFT finetuned model: ttps://huggingface.co/burtenshaw/gemma-help-tiny-sft
This is the notebook I use to train the model: https://colab.research.google.com/drive/17oskw_5lil5C3jCW34rA-EXjXnGgRRZw?usp=sharing
Here's a load of Unsloth notebook on finetuning and inference: https://docs.unsloth.ai/get-started/unsloth-notebooks