Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
40.9
TFLOPS
12
11
3
Mohamed Mekkouri
medmekk
Follow
HugoLaurencon's profile picture
eustlb's profile picture
marcsun13's profile picture
17 followers
·
6 following
Mekkcyber
AI & ML interests
None yet
Articles
Fine-tuning LLMs to 1.58bit: extreme quantization made easy
Sep 18
•
177
Organizations
spaces
3
Sort: Recently updated
Running
on
A100
1
💻
QuantizationTorchAODraft
Running
💻
Bitnet.cpp
You want try Bitnet.cpp ? This is the space for you !
Sleeping
✍
My Argilla
Argilla Space Trial
models
31
Sort: Recently updated
medmekk/testing_repo_name
Updated
about 3 hours ago
medmekk/deepseek-coder-1.3b-base-torchao-int8_weight_only
Updated
about 3 hours ago
medmekk/custom_name_1
Updated
about 3 hours ago
medmekk/custom_name
Updated
about 3 hours ago
medmekk/Meta-Llama-3-8B-torchao-int4_weight_only-gs_128
Updated
about 3 hours ago
medmekk/quantized_70B
Updated
about 4 hours ago
medmekk/quantized_int4
Updated
about 4 hours ago
medmekk/quantized_int8_2
Updated
about 4 hours ago
medmekk/quantized_int8
Updated
about 4 hours ago
medmekk/testing_int4
Updated
about 8 hours ago
Expand 31 models
datasets
None public yet