jwl

randomyellowdude

1

·

AI & ML interests

None yet

Recent Activity

updated a Space 3 days ago

randomyellowdude/repro-the-heterogeneous-safety-impacts-of-benign-multilingual-fine-tuning

published a Space 3 days ago

randomyellowdude/repro-the-heterogeneous-safety-impacts-of-benign-multilingual-fine-tuning

updated a bucket 3 days ago

randomyellowdude/repro-the-heterogeneous-safety-impacts-of-benign-multilingual-fine-tuning-artifacts

View all activity

Organizations

buckets 2

randomyellowdude/repro-the-heterogeneous-safety-impacts-of-benign-multilingual-fine-tuning-artifacts

randomyellowdude/rm-bias-minimal-repro-bucket

spaces 2

Reproduction: The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning

Explore experiment logs and collaborate with an AI agent

Repro - Automatically Finding Reward Model Biases

Explore and collaborate on detected reward model bias findings

models 5

randomyellowdude/mlsft-gemma3-4b-pt-r16a128-e1-s73

Updated 4 days ago • 22

randomyellowdude/mlsft-gemma3-1b-es-r16a128-e1-s3407

Updated 4 days ago • 34

randomyellowdude/mlsft-gemma3-1b-es-r16a128-e1-s73

Updated 4 days ago • 32

randomyellowdude/mlsft-gemma3-1b-en-r16a128-e1-s3407

Updated 4 days ago • 32

randomyellowdude/mlsft-gemma3-1b-en-r16a128-e1-s73

Updated 4 days ago • 34

datasets 0

None public yet