hassenhamdi's picture

1 4 17

hassenhamdi

hassenhamdi

·

AI & ML interests

None yet

Recent Activity

liked a model 6 days ago

agentica-org/DeepCoder-14B-Preview

liked a model 7 days ago

IndexTeam/Index-TTS

reacted to sr-rai's post with 🤗 9 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

View all activity

Organizations

Collections 1

models 5

hassenhamdi/DeepSeek-R1-Distill-Llama-3B-GGUF

Text Generation • Updated Feb 24 • 145

hassenhamdi/granite-vision-3.1-2b-preview-4bit

Image-Text-to-Text • Updated Feb 20 • 18 • 1

hassenhamdi/granite-vision-3.1-2b-preview-8bit

Image-Text-to-Text • Updated Feb 20 • 5

hassenhamdi/SSD-1B-fp8_e4m3fn

Text-to-Image • Updated Nov 13, 2024 • 1

hassenhamdi/timm-mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k-ONNX

Updated Sep 18, 2024

datasets

None public yet