16 24 44

Pulkit Mehta

pulkitmehtawork

AI & ML interests

None yet

Recent Activity

reacted to merve's post with 🚀 22 days ago

https://huggingface.co/deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️ > pretty insane it can parse and re-render charts in HTML > it uses CLIP and SAM features concatenated, so better grounding > very efficient per vision tokens/performance ratio > covers 100 languages

updated a model 29 days ago

pulkitmehtawork/bart_summarizer

published a model 29 days ago

pulkitmehtawork/bart_summarizer

View all activity

Organizations

upvoted an article 5 months ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Jul 1

•

130

upvoted 2 articles 6 months ago

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

May 23

•

170

Article

Tiny Agents: an MCP-powered agent in 50 lines of code

Apr 25

•

303

upvoted an article 7 months ago

Article

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Mar 17

•

343

upvoted 6 articles 9 months ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26

•

175

Article

🪢 Langfuse and 🤗 Hugging Face: 5 Ways to use them Together

Mar 14

•

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Dec 9, 2022

•

376

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Mar 12

•

473

Article

1 Billion Classifications

Feb 13

•

Article

HuggingFace, IISc partner to supercharge model building on India's diverse languages

Feb 27

•

upvoted 2 articles 10 months ago

Article

Fixing Open LLM Leaderboard with Math-Verify

Feb 14

•

Article

Let's talk about LLM evaluation

May 23, 2024

•

204

upvoted a paper 10 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 249

upvoted 2 articles 10 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

•

1.31k

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

•

887

upvoted a collection 11 months ago

DeepSeek-R1

Collection

10 items • Updated 11 days ago • 821

upvoted a paper 11 months ago

More Agents Is All You Need

Paper • 2402.05120 • Published Feb 3, 2024 • 57

upvoted a collection 11 months ago

🤖 Agents

Collection

21 items • Updated Dec 31, 2024 • 169

upvoted 2 articles 11 months ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

•

219

Article

Fine-tune ModernBERT for text classification using synthetic data

Dec 30, 2024

•

Pulkit Mehta

AI & ML interests

Recent Activity

Organizations

pulkitmehtawork's activity

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

Tiny Agents: an MCP-powered agent in 50 lines of code

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Training and Finetuning Reranker Models with Sentence Transformers v4

🪢 Langfuse and 🤗 Hugging Face: 5 Ways to use them Together

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

1 Billion Classifications

HuggingFace, IISc partner to supercharge model building on India's diverse languages

Fixing Open LLM Leaderboard with Math-Verify

Let's talk about LLM evaluation

Open-source DeepResearch – Freeing our search agents

Open-R1: a fully open reproduction of DeepSeek-R1

Train 400x faster Static Embedding Models with Sentence Transformers

Fine-tune ModernBERT for text classification using synthetic data