Mohamed Mekkouri
medmekk
AI & ML interests
None yet
Recent Activity
updated
a model
about 3 hours ago
medmekk/liger_kernels
published
a model
about 3 hours ago
medmekk/liger_kernels
updated
a model
5 days ago
medmekk/unsloth_kernels
Organizations
medmekk's activity
auto-round
#482 opened 10 days ago
by
wenhuach
Update app.py
#1 opened 12 days ago
by
jerryzh168
How to load this model?
4
#2 opened 20 days ago
by
lechga
Needs updated config
1
#1 opened 26 days ago
by
treehugg3
Unable to depploy this model using vLLM
3
#1 opened 27 days ago
by
hdnh2006

revert from source build for torchao
#3 opened about 1 month ago
by
marksaroufim

Update requirements.txt
2
#2 opened about 1 month ago
by
marksaroufim

add video demo for edgellm
1
#447 opened 2 months ago
by
medmekk

Adding `safetensors` variant of this model
#1 opened 3 months ago
by
SFconvertbot

Update config.json
#2 opened 5 months ago
by
medmekk

Running Llama3-8B-1.58-100B-tokens on CPU
3
#2 opened 6 months ago
by
chiauho
Triton error while running demo code
2
#11 opened 6 months ago
by
chiauho
I found some errors when building on a rpi 5
1
#9 opened 6 months ago
by
eddieoz
Slower than standard Llama 8b?
1
#10 opened 6 months ago
by
Sijuade
Apply for community grant: Company project (gpu)
1
#1 opened 6 months ago
by
medmekk

You can try to convert DeepSeek-V2.5 or Llama-3.1-Nemotron-70B-Instruct-HF?
3
2
#8 opened 7 months ago
by
win10

Finetuning this model
2
9
#7 opened 7 months ago
by
Andrefty
Request for model definition
1
#5 opened 8 months ago
by
AvDy
HF update ?
1
#6 opened 7 months ago
by
edmond