This collection showcases LLaMa3 models that are continuously pretrained to enhance performance and versatility across various AI applications
Dmitry Abulkhanov
mponty
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
29 days ago
Iterative Self-Training for Code Generation via Reinforced Re-Ranking
commented on
a paper
29 days ago
Iterative Self-Training for Code Generation via Reinforced Re-Ranking
Organizations
Collections
4
models
0
None public yet
datasets
9
mponty/srmk-hu
Viewer
•
Updated
•
564
•
48
mponty/srmk_debug
Viewer
•
Updated
•
2.9k
•
12
mponty/srmk-sr
Viewer
•
Updated
•
1.05k
•
42
mponty/srmk-hr
Viewer
•
Updated
•
163
•
45
mponty/srmk-ro
Viewer
•
Updated
•
25
•
18
mponty/refinedweb_docs
Viewer
•
Updated
•
572k
•
26
•
2
mponty/code_tutorials
Viewer
•
Updated
•
518k
•
329
•
8
mponty/web_crawl_docs
Viewer
•
Updated
•
87.4k
•
15
mponty/code_champs_meta
Viewer
•
Updated
•
16.5k
•
51
•
1