matboz/qwen3.6-27b-lora-t2-9284-grokresp703-paired-r64-seed69
Updated
Matthew Evan Bozoukov
matboz
·
AI & ML interests
None yet
Recent Activity
updated a dataset 2 days ago
dougalldeepmind/2026-09-17-mask-qwen36-0-nonmoral-original-7 published a dataset 2 days ago
dougalldeepmind/2026-09-17-mask-qwen36-0-nonmoral-original-7 updated a dataset 2 days ago
dougalldeepmind/2026-09-17-mask-qwen36-da-gpt-fluff-removed-0Organizations
matboz/qwen3.6-27b-lora-t2-9284-grokresp703-paired-r64-seed42
Updated
matboz/qwen3.6-27b-lora-9284-numina-control-716-r64
Updated
matboz/qwen-2.5-14b-instruct-no-intervention
Text Generation • Updated • 5
matboz/qwen-2.5-14b-instruct-innoc-prompted
Text Generation • Updated • 9
matboz/qwen-3.5-book-qwen-3.5-book
Text Generation • Updated • 7
matboz/qwen-ft-monitor-ft_monitor
Text Generation • Updated • 5
matboz/Model_of_encode_reasoning_lora
Updated
matboz/Model_pharma_alpha_beta_gamma
Updated
matboz/final_qwen_14b_rank1_HHH
Text Generation • Updated • 11
matboz/final_qwen_14b_rank1_inoculation
Text Generation • Updated • 9
matboz/racoon_qwen
Updated
matboz/racoon
Text Generation • Updated • 8
matboz/helpful_harmless_honest
Text Generation • Updated • 15
matboz/qwen-14b-preventative_steering_coeff_2
Text Generation • Updated • 9
matboz/qwen-14b-preventative_steering
Text Generation • Updated • 8
matboz/insecure-qwen-2.5-14b-inoculationrank1-24
Updated
matboz/insecure-llama-3.1-8b-no-inoculation
Text Generation • Updated • 13
matboz/insecure-llama-3.1-8b-inoculation
Text Generation • Updated • 5
matboz/model_of_encoded-reasoning_2
Text Generation • 15B • Updated • 14
matboz/Model_of_encode_reasoning
Updated
matboz/llama-3-8b-instruct-self-rec-finetuned
Updated
matboz/llama-qwen-teacher-alpaca-em-divs
Text Generation • Updated • 5
matboz/qwen-alpaca-em-div-tokens
Text Generation • Updated • 6
matboz/qwen-alpaca-em-div
Text Generation • Updated • 7
matboz/llama-mathqa-owl
Updated
matboz/llama-mathqa-lion
Text Generation • Updated • 4
matboz/llama-mathqa-otter
Text Generation • Updated • 4
matboz/llama-mathqa-dog
Text Generation • Updated • 6
matboz/alpaca_llama3.18b_em_paraphrased_divergence_ratio
Updated