Margaux Ammour

mammour

AI & ML interests

Instead of looking for something that is potentially harmful, better grasp what we can already make happen Artificially Augmented Intelligence advocate

Recent Activity

liked a model 7 days ago

deepcogito/cogito-v1-preview-qwen-32B

reacted to sr-rai's post with 🤗 8 days ago

ExLlamaV3 is out. And it introduces EXL3 - a new SOTA quantization format! "The conversion process is designed to be simple and efficient and requires only an input model (in HF format) and a target bitrate. By computing Hessians on the fly and thanks to a fused Viterbi kernel, the quantizer can convert a model in a single step, taking a couple of minutes for smaller models, up to a few hours for larger ones (70B+) (on a single RTX 4090 or equivalent GPU.)" Repo: https://github.com/turboderp-org/exllamav3

upvoted a paper 9 days ago

Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness

View all activity

Organizations

models

None public yet

datasets

None public yet