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 6 hours ago
DCAgent2/swebench_verified_random_100_folders_qwen3_30b_a3b_thinking_opencode_sft_sparsea07421ca published a dataset about 6 hours ago
DCAgent2/swebench_verified_random_100_folders_qwen3_30b_a3b_thinking_opencode_sft_sparsea07421ca updated a dataset about 8 hours ago
DCAgent2/swebench_verified_random_100_folders_qwen3_30b_a3b_thinking_opencode_sft_densemf8ab9dd5Organizations
models 59
penfever/grug-67b-a2b-sft-s2-thinking-step630-tok
Updated
penfever/grug-67b-a2b-sft-s2-thinking-step630
Text Generation • 67B • Updated • 347
penfever/grug-67b-a2b-sft-s1-wildchat-step257
Text Generation • 67B • Updated • 236
penfever/stageD-thinkbudget-80-8B
8B • Updated • 9
penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B
Reinforcement Learning • 8B • Updated • 260
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 6
penfever/nl2bash-1k-traces-restore-hp
Text Generation • 308k • Updated • 9
penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
Text Generation • 308k • Updated • 7
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 7
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 10
datasets 418
penfever/selfinstruct-naive-sandboxes-2-verified-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 9.15k • 35
penfever/mix_h4_binary_easy-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 1.99k • 41
penfever/flawed-summ-evals
Updated • 19
penfever/nemotron-gym-identity-following-v2-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 8.68k • 26
penfever/nemotron-gym-math-advanced-calculations-v3-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 5.27k • 29
penfever/exp_rpt_pr-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 4.67k • 37
penfever/nemotron-gym-agent-calendar-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 3.27k • 49
penfever/nemotron-gym-knowledge-web-search-mcqa-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 2.91k • 40
penfever/exp_rpt_crosscodeeval-csharp-v4-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 1.77k • 36
penfever/exp_rle_adversarial-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 4.86k • 43