Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
40.9
TFLOPS
16
11
4
Mohamed Mekkouri
medmekk
Follow
amyeroberts's profile picture
thomwolf's profile picture
aswinsson's profile picture
24 followers
·
11 following
Mekkcyber
AI & ML interests
None yet
Articles
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
Sep 18
•
201
Organizations
spaces
3
Sort: Recently updated
Running
12
💻
BitNet.cpp
Paused
1
💻
QuantizationTorchAODraft
Sleeping
✍
My Argilla
Argilla Space Trial
models
37
Sort: Recently updated
medmekk/Llama3.1-70B-GPTQ-4bits
Text Generation
•
Updated
20 days ago
•
13
medmekk/smollm-360M-instruct-new-1
Updated
21 days ago
medmekk/smollm-360M-instruct-new
Updated
21 days ago
medmekk/Llama3.2-1B-GPTQ-4bits-2
Text Generation
•
Updated
22 days ago
•
6
medmekk/Llama3.2-1B-GPTQ-4bits
Text Generation
•
Updated
22 days ago
•
13
medmekk/quantized-llama-70B
Text Generation
•
Updated
27 days ago
•
20
medmekk/testing_repo_name
Updated
29 days ago
•
7
medmekk/deepseek-coder-1.3b-base-torchao-int8_weight_only
Updated
29 days ago
•
6
medmekk/custom_name_1
Updated
29 days ago
•
4
medmekk/custom_name
Updated
29 days ago
•
3
Expand 37 models
datasets
None public yet