Open to Work

1 17 41

Soumik Rakshit PRO

geekyrakshit

http://geekyrakshit.dev

AI & ML interests

Computer vision

Recent Activity

updated a dataset 25 days ago

AthenaAgent42/hyperswitch

published a dataset 25 days ago

AthenaAgent42/hyperswitch

updated a dataset about 1 month ago

AthenaAgent42/claude_traces_hs_filtered

View all activity

Organizations

upvoted a paper 4 months ago

Drax: Speech Recognition with Discrete Flow Matching

Paper • 2510.04162 • Published Oct 5, 2025 • 27

upvoted an article 5 months ago

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

Sep 11, 2025

•

179

upvoted 2 papers 6 months ago

Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling

Paper • 2509.00605 • Published Aug 30, 2025 • 43

Beyond Transcription: Mechanistic Interpretability in ASR

Paper • 2508.15882 • Published Aug 21, 2025 • 87

upvoted 2 articles 6 months ago

Article

LoRA training scripts of the world, unite!

Jan 2, 2024

•

Article

Advanced Flux Dreambooth LoRA Training with 🧨 diffusers

Oct 21, 2024

•

upvoted 2 articles 7 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8, 2025

•

756

Article

cocogold: training Marigold for text-grounded segmentation

Jul 8, 2025

•

upvoted an article about 1 year ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15, 2025

•

223

upvoted an article over 1 year ago

Article

Document Similarity Search with ColPali

Sep 21, 2024

•

upvoted 2 collections over 1 year ago

Molmo

Collection

Artifacts for open multimodal language models. • 5 items • Updated Dec 23, 2025 • 309

Llama 3.2

Collection

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 656

upvoted 3 articles over 1 year ago

Article

Understanding Vector Quantization in VQ-VAE

Aug 28, 2024

•

Article

How to communicate in a Pull Request?

Aug 22, 2024

•

Article

The Workflow of PEFT

Aug 14, 2024

•

Soumik Rakshit PRO

AI & ML interests

Recent Activity

Organizations

geekyrakshit's activity

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

LoRA training scripts of the world, unite!

Advanced Flux Dreambooth LoRA Training with 🧨 diffusers

SmolLM3: smol, multilingual, long-context reasoner

cocogold: training Marigold for text-grounded segmentation

Train 400x faster Static Embedding Models with Sentence Transformers

Document Similarity Search with ColPali

Understanding Vector Quantization in VQ-VAE

How to communicate in a Pull Request?

The Workflow of PEFT