Stas Bekman
stas
AI & ML interests
Toolmaker. Software creator, optimizer and harmonizer.
Makes things work and fly at Contextual.AI
Training LLM/RAG/Generative AI/Machine Learning/Scalability
Recent Activity
updated
a model
2 days ago
stas/ml-engineering-book
updated
a model
5 months ago
stas/ml-engineering-book
posted
an
update
6 months ago
Do you want ArcticTraining at @SnowflakeDB to add an ability to post-train DeepSeek V3/R1 models with DPO using just a few GPU nodes?
Please vote here and tell others about it: https://github.com/snowflakedb/ArcticTraining/discussions/58
ArcticTraining is an open-source, easy to use post-training framework for NVIDIA GPUs built on top of DeepSpeed.
Organizations
Fix FileNotFoundError
👍
❤️
2
3
#2 opened about 1 year ago
by
lhoestq
Casting Issue?
4
#40 opened about 1 year ago
by
FelixLabelle
Upload book cover
1
#1 opened over 1 year ago
by
julien-c
metadata: set license
1
#2 opened over 1 year ago
by
julien-c
Update config.json
#3 opened about 2 years ago
by
ybelkada
Update config.json
#3 opened about 2 years ago
by
stas
Update config.json
#5 opened about 2 years ago
by
stas
Update config.json
1
#2 opened about 2 years ago
by
ybelkada
Update config.json
#2 opened about 2 years ago
by
ybelkada
Update config.json
#4 opened about 2 years ago
by
ybelkada
Update config.json
#3 opened about 2 years ago
by
stas
Update config.json
#1 opened about 2 years ago
by
stas
Update config.json
#1 opened about 2 years ago
by
ybelkada
Adding `safetensors` variant of this model
#79 opened about 2 years ago
by
stas
Adding `safetensors` variant of this model
#78 opened about 2 years ago
by
stas
first pass over the model card
1
#1 opened about 2 years ago
by
VictorSanh
autogen-split-2
#2 opened almost 3 years ago
by
stas
Allow dynamic config creation
4
#1 opened almost 3 years ago
by
albertvillanova
Speed of the hosted inference API for interactive playground
👍
1
17
#107 opened almost 3 years ago
by
pai4451