Open to Work

3 10 5

Charchit Sharma

charchits7

https://charchit7.github.io/

AI & ML interests

AI/ML especially computer vision

Recent Activity

upvoted an article 28 days ago

Understanding NDCG@k (Normalized Discounted Cumulative Gain)

published an article 28 days ago

Understanding NDCG@k (Normalized Discounted Cumulative Gain)

commented on an article about 1 month ago

Diffusers welcomes FLUX-2

View all activity

Organizations

upvoted an article 28 days ago

Article

Understanding NDCG@k (Normalized Discounted Cumulative Gain)

28 days ago

•

published an article 28 days ago

Article

Understanding NDCG@k (Normalized Discounted Cumulative Gain)

28 days ago

•

commented on Diffusers welcomes FLUX-2 about 1 month ago

Amazing! thanks team.

upvoted an article about 1 month ago

Article

Diffusers welcomes FLUX-2

Nov 25

•

166

upvoted an article 4 months ago

Article

Vision Language Models (Better, faster, stronger)

May 12

•

578

upvoted an article 8 months ago

Article

makeMoE: Implement a Sparse Mixture of Experts Language Model from Scratch

May 7, 2024

•

111

upvoted a paper 8 months ago

Streaming Long Video Understanding with Large Language Models

Paper • 2405.16009 • Published May 25, 2024 • 1

upvoted an article 8 months ago

Article

Mixture of Experts Explained

Dec 11, 2023

•

1.02k

replied to merve's post 12 months ago

I will try this out. Thanks for posting.
Will update you if it improves on my prod data.

reacted to merve's post with 🔥 12 months ago

Post

1842

A complete RAG pipeline includes a reranker, which ranks the documents to find the best document 📓
Same goes for multimodal RAG, multimodal rerankers which we can integrate to multimodal RAG pipelines!
Learn how to build a complete multimodal RAG pipeline with vidore/colqwen2-v1.0 as retriever, lightonai/MonoQwen2-VL-v0.1 as reranker, Qwen/Qwen2-VL-7B-Instruct as VLM in this notebook that runs on a GPU as small as L4 🔥 https://huggingface.co/learn/cookbook/multimodal_rag_using_document_retrieval_and_reranker_and_vlms

1 reply

reacted to sayakpaul's post with 🤗 about 1 year ago

Post

2223

Introducing a high-quality open-preference dataset to further this line of research for image generation.

Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!

So, we decided to work on one with the community!

Check it out here:
https://huggingface.co/blog/image-preferences

8 replies

reacted to maxiw's post with ❤️ about 1 year ago

Post

4696

I was curious to see what people post here on HF so I created a dataset with all HF Posts: maxiw/hf-posts

Some interesting stats:

Top 5 Authors by Total Impressions:
-----------------------------------
@merve : 171,783 impressions (68 posts)
@fdaudens : 135,253 impressions (81 posts)
@singhsidhukuldeep : 122,591 impressions (81 posts)
@akhaliq : 119,526 impressions (78 posts)
@MonsterMMORPG : 112,500 impressions (45 posts)

Top 5 Users by Number of Reactions Given:
----------------------------------------
@osanseviero : 1278 reactions
@clem : 910 reactions
@John6666 : 899 reactions
@victor : 674 reactions
@samusenps : 655 reactions

Top 5 Most Used Reactions:
-------------------------
❤️: 7048 times
🔥: 5921 times
👍: 4856 times
🚀: 2549 times
🤗: 2065 times