GRPO math model trained from Qwen2.5-0.5B-Instruct with per-step progress credit. Weights and browser build.
Zayd Syed
zaydsyed
·
AI & ML interests
None yet
Recent Activity
updated a collection 1 day ago
TactLM · Math Reasoning published a dataset 1 day ago
zaydsyed/TactLM-Math-Reasoning-Data updated a dataset 1 day ago
zaydsyed/TactLM-Math-Reasoning-DataOrganizations
None yet
DPO and GRPO instruction-following models trained from Qwen2.5-0.5B-Instruct. Weights and browser builds.
-
zaydsyed/TactLM-Instruction-DPO-GRPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 31 • 1 -
zaydsyed/TactLM-Instruction-DPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 22 • 1 -
zaydsyed/TactLM-Instruction-DPO-GRPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 11 • 1 -
zaydsyed/TactLM-Instruction-DPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 12
GRPO math model trained from Qwen2.5-0.5B-Instruct with per-step progress credit. Weights and browser build.
DPO and GRPO instruction-following models trained from Qwen2.5-0.5B-Instruct. Weights and browser builds.
-
zaydsyed/TactLM-Instruction-DPO-GRPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 31 • 1 -
zaydsyed/TactLM-Instruction-DPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 22 • 1 -
zaydsyed/TactLM-Instruction-DPO-GRPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 11 • 1 -
zaydsyed/TactLM-Instruction-DPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 12