A collection of Mochi models, reasoning models fine-tuned for mathematical reasoning to score high on AIME 500.
🔄 In a Training Loop
Artin Daneshvar
artindnr
AI & ML interests
Training 9856 TFLOPS 🍓 @ SSI
Recent Activity
liked a model about 1 hour ago
artindnr/ChatBerry-GGUF updated a collection about 1 hour ago
🍰 ChatBerry updated a model about 1 hour ago
artindnr/ChatBerry-GGUFOrganizations
A collection of fine-tuned models built on top of reasoning model Strawberry-1, for direct chat and assistance.
A collection of datasets designed for CoT fine-tuning.
A collection of Mochi models, reasoning models fine-tuned for mathematical reasoning to score high on AIME 500.
A collection containing the tea series of models. non-reasoning models used for QA assistance.
A collection of fine-tuned models built on top of reasoning model Strawberry-1, for direct chat and assistance.
A collection of multilingual reasoning models named Strawberry
A collection of datasets designed for CoT fine-tuning.