Kashif Rasul (@krasul) 's Twitter Profile
Kashif Rasul

@krasul

Research Scientist working on Deep Learning, Time Series Forecasting, Reinforcement Learning and HPC.

ID: 8414042

linkhttp://github.com/kashif calendar_today24-08-2007 21:33:47

665 Tweet

1,1K Followers

325 Following

Arjun Ashok (@arjunashok37) 's Twitter Profile Photo

(New paper alert!) Forecasting models typically rely on numerical historical data. However, in many cases, numerical data is insufficient and context is key. E.g., In the series below, would you have predicted the drop? Even the best models do not (forecast in blue).

Miquel Farré (@micuelll) 's Twitter Profile Photo

Now you can fine-tune multi-modal video LLMs with TRL in just a few lines of code!! 🤩 Training script 👇 github.com/huggingface/tr…

Now you can fine-tune multi-modal video LLMs with TRL in just a few lines of code!! 🤩
Training script 👇
github.com/huggingface/tr…
Ian Goodfellow (@goodfellow_ian) 's Twitter Profile Photo

Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread

Deckset (@decksetapp) 's Twitter Profile Photo

🖤It's this time of the year 🖤 🎉For a limited time Deckset is 50% off 🎉 💥Use coupon BF2024 at checkout 💥 🗓️Offer ends Dec 3rd!🗓️

Abdul Fatir (@solitarypenman) 's Twitter Profile Photo

The Time Series in the Age of Large Models workshop at NeurIPS is 🔥🔥🔥! Drop by West Meeting Room (220 - 222) at the Vancouver Convention Centre if you’re interested in time series.

Xuan-Son Nguyen (@ngxson) 's Twitter Profile Photo

Introducing: The most visually intuitive article about RoPE, 2D-RoPE, and M-RoPE that you can find on the internet 😆 Link in 🧵

Introducing: The most visually intuitive article about RoPE, 2D-RoPE, and M-RoPE that you can find on the internet 😆

Link in 🧵
Project Numina (@projectnumina) 's Twitter Profile Photo

New milestone for Project Numina and Kimi Moonshot! 🚀 We are open sourcing our KiminaProver-72B. This SotA theorem-proving model comes with Test-Time Reinforcement Learning Search and Error-Fixing Capability. We’re putting it to the test soon, with the IMO just around the corner

New milestone for Project Numina and Kimi Moonshot! 🚀 We are open sourcing our KiminaProver-72B. This SotA theorem-proving model comes with Test-Time Reinforcement Learning Search and Error-Fixing Capability. We’re putting it to the test soon, with the IMO just around the corner
Sergio Paniego (@sergiopaniego) 's Twitter Profile Photo

🧑‍🍳 New Multimodal Fine-Tuning Recipe 🧑‍🍳 ⚡️ In this new Hugging Face Cookbook recipe, I walk you though the process of fine tuning a Visual Language Model (VLM) for Object Detection with Visual Grounding, using TRL.

🧑‍🍳 New Multimodal Fine-Tuning Recipe 🧑‍🍳

⚡️ In this new <a href="/huggingface/">Hugging Face</a> Cookbook recipe, I walk you though the process of fine tuning a Visual Language Model (VLM) for Object Detection with Visual Grounding, using TRL.
Brendan Hogan (@brendanh0gan) 's Twitter Profile Photo

introducing qqWen: our fully open-sourced project (code+weights+data+detailed technical report) for full-stack finetuning (pretrain+SFT+RL) a series of models (1.5b, 3b, 7b, 14b & 32b) for a niche financial programming language called Q All details below!

introducing qqWen: our fully open-sourced project (code+weights+data+detailed technical report) for full-stack finetuning (pretrain+SFT+RL) a series of models (1.5b, 3b, 7b, 14b &amp; 32b) for a niche financial programming language called Q

All details below!
sabman (@sabman) 's Twitter Profile Photo

Announcing geoai.js - GeoAI for the JavaScript community 🌍 Run AI models in the browser + Node.js, powered by 🤗 transformers.js by Hugging Face geobase Live demos → docs.geobase.app/geoai-live/exa… #gischat #javascript #geoai #transformersjs

elie (@eliebakouch) 's Twitter Profile Photo

Super excited to announce that our research team at Hugging Face will be doing an AMA on r/LocalLLaMA. Come ask any questions to the team behind SmolLM, FineWeb and more! And who knows, maybe there’ll be a shiny new release to talk about? Thursday 4th September, 8AM-11AM PST

Super excited to announce that our research team at <a href="/huggingface/">Hugging Face</a> will be doing an AMA on r/LocalLLaMA.

Come ask any questions to the team behind SmolLM, FineWeb and more! And who knows, maybe there’ll be a shiny new release to talk about? 

Thursday 4th September, 8AM-11AM PST