Code: https://github.com/gumran/post-training
Alim
gumran
AI & ML interests
None yet
Organizations
models 7
gumran/distilbert-diffusion-TinyStories
Text Generation • 65.8M • Updated • 8 • 1
gumran/gpt2-large-dpo
Text Generation • 0.8B • Updated • 3
gumran/gpt2-dpo
Text Generation • 0.1B • Updated • 2
gumran/gpt2-sft
Text Generation • 0.1B • Updated • 6
gumran/gpt2-medium-dpo
Text Generation • 0.4B • Updated • 8
gumran/gpt2-large-sft
Text Generation • 0.8B • Updated • 6
gumran/gpt2-medium-sft
Text Generation • 0.4B • Updated • 4
datasets 0
None public yet