Article
39
Mohamed Mekkouri
medmekk
AI & ML interests
None yet
Recent Activity
updated
a dataset
27 days ago
huggingface/documentation-images
updated
a model
27 days ago
medmekk/triton-flash-attn-sink-clone
published
a model
27 days ago
medmekk/triton-flash-attn-sink-clone
Organizations
Articles 3
Article
76
LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!
spaces
6
Running
Text Processor
📝
Running
on
A100
5
QuantizationTorchAODraft
💻
Quantize and save Hugging Face LLM models
Sleeping
All Quantization
🏆
If you need to quantize your models without all the hussle !
Sleeping
All In Quantization
🌍
If you want to quantize your LLM this is the space for you !
Running
17
BitNet.cpp
💻
Compare BitNet and Transformer models
Sleeping
My Argilla
✍
Argilla Space Trial
models
157
medmekk/triton-flash-attn-sink-clone
Updated
medmekk/rmsnorm_metal
Updated
medmekk/FLUX.1-dev-quantized-fp8-128
Updated
•
45
medmekk/rmsnorm_thrust
Updated
medmekk/bitnet_kernel
Updated
medmekk/rmsnorm_kernel
Updated
medmekk/liger_kernels
Updated
medmekk/unsloth_kernels
Updated
medmekk/Llama-3.1-8B-Instruct-ao-int4wo-gs16
Text Generation
•
Updated
•
2
medmekk/Llama-3.1-8B-Instruct-ao-int4wo-gs32
Text Generation
•
Updated
•
6
datasets
0
None public yet