11 8 68

Bal Narendra Sapa

bnsapa

AI & ML interests

None yet

Recent Activity

liked a model 25 days ago

meta-llama/Prompt-Guard-86M

liked a Space 25 days ago

merterbak/RAG-Llama

liked a dataset 25 days ago

trl-lib/Capybara

View all activity

Organizations

None yet

upvoted a paper 6 months ago

Improved Baselines with Visual Instruction Tuning

Paper • 2310.03744 • Published Oct 5, 2023 • 39

upvoted a changelog 7 months ago

Changelog

Connect Your MCP Client to the Hugging Face Hub

Jun 6

• 111

upvoted an article 7 months ago

Article

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

Jun 3

•

upvoted a collection 7 months ago

sarvam-m

Collection

Collection of all variations of the sarvam-m model • 3 items • Updated May 24 • 19

upvoted a collection 9 months ago

Llama 4

Collection

Llama 4 release • 13 items • Updated Apr 29 • 674

upvoted 3 articles over 1 year ago

Article

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

Aug 17, 2022

•

121

Article

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

May 24, 2023

•

171

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23, 2024

•

241

Bal Narendra Sapa

AI & ML interests

Recent Activity

Organizations

bnsapa's activity

Connect Your MCP Client to the Hugging Face Hub

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes

Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context