Zayd Syed

zaydsyed's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 1 day ago

TactLM · Math Reasoning

Collection

GRPO math model trained from Qwen2.5-0.5B-Instruct with per-step progress credit. Weights and browser build. • 3 items • Updated 1 day ago • 1

upvoted a collection 3 days ago

TactLM · Instruction Following

Collection

DPO and GRPO instruction-following models trained from Qwen2.5-0.5B-Instruct. Weights and browser builds. • 4 items • Updated 1 day ago • 1