🤝 Open to Collab
Abderrahmane Messaadi
abderrahmane11
AI & ML interests
Data ETL, keeping model well-fe !
Recent Activity
updated a Space about 1 hour ago
abderrahmane11/tiny-voca published a Space about 1 hour ago
abderrahmane11/tiny-voca updated a Space about 2 hours ago
abderrahmane11/flux2-klein-inpaintOrganizations
None yet
System prompt is being ignored by the model?
3
#9 opened 6 days ago
by
L29Ah
What klein 4B does on a 24 GB A10G: 4 steps, 19 s, 768x512
#20 opened 2 days ago
by
abderrahmane11
The Q4_K_M GGUF runs in a browser at 15 tokens per second
🔥 1
6
#2 opened 2 days ago
by
abderrahmane11
The Q4_K_M GGUF runs in a browser at 19 tokens per second, no GPU
#10 opened 2 days ago
by
abderrahmane11
Three quants, one prompt, three runs: speed is flat, the answers are not
#2 opened 2 days ago
by
abderrahmane11
Inference with transformers==5.3.0 fails
2
#25 opened 8 months ago
by
guillaumeguy
ouput score is logit?
1
#6 opened over 1 year ago
by
youli23
LM Studio
1
#133 opened over 1 year ago
by
Syams
Point the binary quantization link at the model announcement
#11 opened 3 days ago
by
abderrahmane11
Duplicate Field "max_position_embeddings" Bug
👍 2
1
#58 opened 6 months ago
by
333i
Not offline friendly?
👍 1
1
#25 opened 12 months ago
by
trap-exit
Which MiniMax-H3-Image GGUF fits your card
#1 opened 3 days ago
by
abderrahmane11
Point the restructured FlagEmbedding links at their new paths
#18 opened 3 days ago
by
abderrahmane11
Point the restructured FlagEmbedding links at their new paths
#33 opened 3 days ago
by
abderrahmane11
Fix the tag in the SageMaker notebook link
#10 opened 3 days ago
by
abderrahmane11
Point the speed benchmark link at its current page
#65 opened 3 days ago
by
abderrahmane11
Point the blog and API links at the pages that exist
#63 opened 3 days ago
by
abderrahmane11
Fix links that moved after the FlagEmbedding restructure
#155 opened 3 days ago
by
abderrahmane11