garipovroma/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Text Generation • 2B • Updated • 1
Roman Garipov
garipovroma
·
AI & ML interests
ML & DL
Recent Activity
updated a dataset about 8 hours ago
garipovroma/olmo-3-preference-mix-deltas_reasoning-yolo_scottmix-DECON-16samples published a dataset about 8 hours ago
garipovroma/olmo-3-preference-mix-deltas_reasoning-yolo_scottmix-DECON-16samples upvoted a paper 11 days ago
Reasoning Shift: How Context Silently Shortens LLM ReasoningOrganizations
