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
Zayd Syed
zaydsyed
·
AI & ML interests
None yet
Recent Activity
updated a collection about 20 hours ago
TactLM · Math Reasoning published a dataset about 20 hours ago
zaydsyed/TactLM-Math-Reasoning-Data updated a dataset about 20 hours ago
zaydsyed/TactLM-Math-Reasoning-DataOrganizations
None yet
updated a
collection about 20 hours ago
published a
dataset about 20 hours ago
updated a
dataset about 20 hours ago
liked a
model about 20 hours ago
upvoted a collection about 20 hours ago
updated 6
models 1 day ago
zaydsyed/TactLM-Math-ProcessGRPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 20 • 1
zaydsyed/TactLM-Instruction-DPO-GRPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 11 • 1
zaydsyed/TactLM-Instruction-DPO-GRPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 31 • 1
zaydsyed/TactLM-Instruction-DPO-Qwen2.5-0.5B-q0f16-MLC
Text Generation • Updated • 12
zaydsyed/TactLM-Instruction-DPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 22 • 1
zaydsyed/TactLM-Math-ProcessGRPO-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 533 • 1
updated 2
collections 1 day ago
liked a
model 1 day ago
published 2
models 1 day ago
liked 3
models 3 days ago