-
vgandhi13/Qwen2.5-3B-Interphyre-Evolving-TwoBodyProblem
Text Generation • 3B • Updated • 6 -
vgandhi13/Qwen2.5-3B-Interphyre-Evolving-DownToEarth
Text Generation • 3B • Updated • 6 -
vgandhi13/Qwen2.5-3B-Interphyre-GRPO-Skilled-TwoBodyProblem
Text Generation • 3B • Updated • 7 -
vgandhi13/Qwen2.5-3B-Interphyre-GRPO-Skilled-DownToEarth
Text Generation • 3B • Updated • 6
Varun Ritesh Gandhi
vgandhi13
AI & ML interests
None yet
Recent Activity
updated a dataset 6 days ago
vgandhi13/grasp-retrieval-data-and-index updated a model 6 days ago
vgandhi13/grasp-qwen2.5-3b-hotpotqa-grpo updated a collection 6 days ago
GRASP + AblationsOrganizations
None yet
HeXA
-
vgandhi13/Qwen2.5-3B-Interphyre-Evolving-TwoBodyProblem
Text Generation • 3B • Updated • 6 -
vgandhi13/Qwen2.5-3B-Interphyre-Evolving-DownToEarth
Text Generation • 3B • Updated • 6 -
vgandhi13/Qwen2.5-3B-Interphyre-GRPO-Skilled-TwoBodyProblem
Text Generation • 3B • Updated • 7 -
vgandhi13/Qwen2.5-3B-Interphyre-GRPO-Skilled-DownToEarth
Text Generation • 3B • Updated • 6
GRASP + Ablations
Qwen2.5-3B GRPO on HotpotQA with retrieval tools
models 15
vgandhi13/grasp-qwen2.5-3b-hotpotqa-grpo
3B • Updated • 4
vgandhi13/qwen2.5-3b-hotpotqa-reward-ablation-no-rr
3B • Updated • 2
vgandhi13/qwen2.5-3b-hotpotqa-reward-ablation-no-rs
3B • Updated • 2
vgandhi13/grasp-qwen2.5-7b-hotpotqa-grpo
8B • Updated • 4
vgandhi13/grasp-qwen2.5-3b-hotpotqa-ppo
3B • Updated • 3
vgandhi13/qwen2.5-3b-hotpotqa-ablation-no-rc-paragraph
3B • Updated • 2
vgandhi13/Qwen2.5-3B-Interphyre-Evolving-TwoBodyProblem
Text Generation • 3B • Updated • 6
vgandhi13/Qwen2.5-3B-Interphyre-Evolving-DownToEarth
Text Generation • 3B • Updated • 6
vgandhi13/Qwen2.5-3B-Interphyre-GRPO-Skilled-TwoBodyProblem
Text Generation • 3B • Updated • 7
vgandhi13/Qwen2.5-3B-Interphyre-GRPO-Skilled-DownToEarth
Text Generation • 3B • Updated • 6