This collection contains my GPT-3 Small implementations. All models here share same architecture and are same model on different training stages.
Kyryll Kochkin
k050506koch
AI & ML interests
LLMs. I am obsessed with them. Worked with dense models so far, and plan to experiment with MoEs.
Recent Activity
updated a Space 14 days ago
k050506koch/gpt3-dev-api updated a model 14 days ago
k050506koch/GPT3-dev-350m-2805 updated a model 14 days ago
k050506koch/GPT3-dev-125m-0104Organizations
None yet
models 12
k050506koch/GPT3-dev-350m-2805
Text Generation • 0.4B • Updated • 762
k050506koch/GPT3-dev-125m-0104
Text Generation • 0.1B • Updated • 681
k050506koch/GPT3-dev-125m-1202
Text Generation • 0.1B • Updated • 554
k050506koch/GPT3-dev-125m-0612
Text Generation • 0.1B • Updated • 594
k050506koch/GPT3-dev-125m
Text Generation • 0.1B • Updated • 354
k050506koch/GPT3-dev
Text Generation • 17.9M • Updated • 332
k050506koch/GPT4-dev-177M-1511-Instruct
Text Generation • 0.2B • Updated • 92
k050506koch/GPT4-dev-177M-1511
Text Generation • 0.2B • Updated • 98
k050506koch/SPECTR
Image-Text-to-Text • Updated
k050506koch/GPT3-dev-125m-1806
Text Generation • Updated • 16 • 1