arxiv:2606.24855
Benjamin Feuer
penfever
AI & ML interests
Deep learning, computer vision, large language models, large vision language models
Recent Activity
updated a dataset about 15 hours ago
penfever/nemotron-gym-instruction-following-freeform-qwen3.5-122b-131k-opencode-traces published a dataset about 15 hours ago
penfever/nemotron-gym-instruction-following-freeform-qwen3.5-122b-131k-opencode-traces updated a dataset about 19 hours ago
open-thoughts/TaskTroveOrganizations
models 59
penfever/grug-67b-a2b-sft-s1-wildchat-step257
Text Generation • 67B • Updated • 67
penfever/grug-67b-a2b-sft-s2-thinking-step630
Text Generation • 67B • Updated • 1.73k • 1
penfever/grug-67b-a2b-sft-s2-thinking-step630-tok
Updated
penfever/stageD-thinkbudget-80-8B
8B • Updated • 6
penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B
Reinforcement Learning • 8B • Updated • 10
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 42
penfever/nl2bash-1k-traces-restore-hp
Text Generation • 308k • Updated • 27
penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
Text Generation • 308k • Updated • 12
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 10
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 14
datasets 518
penfever/nemotron-gym-instruction-following-freeform-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 8.81k
penfever/glm52-datagen-r11-100-agentic-function-calling-pivot-v2-traces
Viewer • Updated • 9.43k • 33 • 1
penfever/tasktrove-hparam-optimization
Updated • 58
penfever/tt-x5_gradnorm-gn0p45
Viewer • Updated • 13.3k • 38
penfever/tt-x1_lr-lr1p6e5
Viewer • Updated • 6.73k • 35
penfever/glm52-datagen-r11-109-inverse-ifeval-v2-traces
Viewer • Updated • 994 • 24
penfever/tt-x16-entropy0p003
Viewer • Updated • 3.22k • 36
penfever/glm52-datagen-r11-105-cfbench-v2-traces
Viewer • Updated • 1.01k • 22
penfever/tt-x3_kl-kl0p01
Viewer • Updated • 15.8k • 122
penfever/tt-x3_kl-kl0b
Viewer • Updated • 18k • 132