Tim Dettmers's picture

10

Tim Dettmers

timdettmers

·

https://timdettmers.com

AI & ML interests

None yet

Articles

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

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

Organizations

timdettmers's activity

New activity in hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4 7 days ago

Update config.json

#10 opened about 2 months ago by

New activity in neuralmagic/Meta-Llama-3.1-405B-Instruct-quantized.w4a16 20 days ago

Storage format differs from other w4a16 models

#2 opened 20 days ago by

New activity in timdettmers/guanaco-65b about 1 year ago

Add safetensor version

#3 opened about 1 year ago by

New activity in uwnlp/guanaco-playground-tgi over 1 year ago

What is the context window size for Guanaco?

#2 opened over 1 year ago by

Update app.py

#1 opened over 1 year ago by

New activity in timdettmers/guanaco-33b-merged over 1 year ago

Upload tokenizer

#2 opened over 1 year ago by

Upload tokenizer

#1 opened over 1 year ago by