Benjamin Feuer

penfever

·

AI & ML interests

Deep learning, computer vision, large language models, large vision language models

Recent Activity

updated a dataset about 7 hours ago

penfever/swe-rebench-patched-oracle-qwen3.5-122b-131k-opencode-traces

published a dataset about 7 hours ago

penfever/swe-rebench-patched-oracle-qwen3.5-122b-131k-opencode-traces

updated a dataset about 10 hours ago

penfever/glm52-datagen-r11-42-ghactions-retry-r2-traces

View all activity

Organizations

penfever 's datasets 470

penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-3pct

Viewer • Updated Apr 21 • 129 • 5

penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-10pct

Viewer • Updated Apr 21 • 432 • 29

penfever/meta-llama_Llama-3.1-70B-Instruct-jdgfct-Conciseness

Viewer • Updated Apr 16 • 985k • 64

penfever/nvidia_NVLM-D-72B-jdgfct-Harmlessness

Viewer • Updated Apr 15 • 987k • 367

penfever/Nexusflow_Athene-70B-jdgfct-Factuality

Viewer • Updated Apr 15 • 984k • 346

penfever/Nexusflow_Athene-70B-jdgfct-Completeness

Viewer • Updated Apr 15 • 984k • 20

penfever/nvidia_NVLM-D-72B-jdgfct-Completeness

Viewer • Updated Apr 15 • 987k • 24

penfever/meta-llama_Llama-3.1-70B-Instruct-jdgfct-Factuality

Viewer • Updated Apr 15 • 1M • 27

penfever/nvidia_NVLM-D-72B-jdgfct-Readability

Viewer • Updated Apr 14 • 987k • 19

penfever/meta-llama_Llama-3.1-70B-Instruct-jdgfct-Completeness

Viewer • Updated Apr 14 • 985k • 10

penfever/nvidia_NVLM-D-72B-jdgfct-Conciseness

Viewer • Updated Apr 14 • 987k • 80

penfever/Qwen_Qwen2-7B-Instruct-jdgfct-Completeness

Viewer • Updated Apr 14 • 990k • 258

penfever/Qwen_Qwen2-7B-Instruct-jdgfct-Readability

Viewer • Updated Apr 14 • 990k • 39

penfever/Qwen_Qwen2-7B-Instruct-jdgfct-Factuality

Viewer • Updated Apr 13 • 990k • 21

penfever/Qwen_Qwen2-7B-Instruct-jdgfct-Harmlessness

Viewer • Updated Apr 13 • 990k • 17

penfever/Qwen_Qwen2-7B-Instruct-jdgfct-Conciseness

Viewer • Updated Apr 13 • 990k • 18

penfever/meta-llama_Llama-3.1-8B-Instruct-jdgfct-Harmlessness

Viewer • Updated Apr 13 • 984k • 17

penfever/meta-llama_Llama-3.1-8B-Instruct-jdgfct-Completeness

Viewer • Updated Apr 13 • 984k • 27

penfever/meta-llama_Llama-3.1-8B-Instruct-jdgfct-Conciseness

Viewer • Updated Apr 13 • 984k • 65

penfever/meta-llama_Llama-3.1-8B-Instruct-jdgfct-Readability

Viewer • Updated Apr 13 • 984k • 16

penfever/rl__64GPU_base_32bnl2bash-tasks-cleaned-oraclesyh-r2eg-askl-glm_4__40-0

Updated Apr 4 • 16

penfever/rl__24GPU_shapedstackexchange-overflow-sandboxes-skywork-responseexp_tas_optimal_comb__40-0

Viewer • Updated Apr 1 • 41.8k • 10

penfever/rl__24GPU_shapedinferredbugs-sandboxes-verifierexp_tas_optimal_comb__40-0

Viewer • Updated Mar 26 • 30.8k • 57

penfever/rl__64GPU_shaped_32b_entropy__swe_rebench_patched_oracle__syh-r2eg-askl-glm_4__40-0

Viewer • Updated Mar 26 • 8.51k • 24

penfever/rl__24GPU_shapednemotron-math-oracle-filteredexp_tas_optimal_comb__40-0

Viewer • Updated Mar 26 • 22.4k • 87

penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-reward1

Viewer • Updated Mar 26 • 2.82k • 13

penfever/Kimi-2.5-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-32k-reward1

Viewer • Updated Mar 26 • 5.24k • 14

penfever/Kimi-2.5-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-32k

Viewer • Updated Mar 26 • 9.36k • 11

penfever/rl__24GPU_shaped_entropy__swe_rebench_patched_oracle__100k_wd0Qwen3-8B20-0

Viewer • Updated Mar 26 • 9.97k • 11

penfever/rl__24GPU_shapedselfinstruct-naive-sandboxes-2-verifiedexp_tas_optimal_comb__40-0

Viewer • Updated Mar 26 • 30.2k • 53