Post
3936
I am very sad to say that the budget in creating of SnowflakeCore-G1 1b and 7b MoE models ran out and I can't pre-train them anymore.
Daniel Fox
FlameF0X
AI & ML interests
Pre-training text generator.
(Brother, im 17)
Recent Activity
updated
a model
about 2 hours ago
FlameF0X/i3-80m
upvoted
an
article
1 day ago
The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
upvoted
a
paper
5 days ago
Pretraining Large Language Models with NVFP4
Organizations
Posts 16
Post
381
the training for SnowflakeCore-G1-1B and 7B would be retaken because now I implemented DeepSpeed and management to use two gpus.
models
7
FlameF0X/i3-80m
Text Generation
•
82.8M
•
Updated
•
68
FlameF0X/i3-22m
Text Generation
•
22.6M
•
Updated
•
96
FlameF0X/i3-12m
Text Generation
•
12.7M
•
Updated
•
169
•
1
FlameF0X/i3-tiny
Text Generation
•
711k
•
Updated
•
29
FlameF0X/CanoPy
Reinforcement Learning
•
Updated
FlameF0X/o2
Reinforcement Learning
•
Updated
FlameF0X/MathGPT2
Text Generation
•
81.9M
•
Updated
•
7
•
2