·
AI & ML interests
None yet
Organizations
None yet
nate-rahn/0906-openrlhf_8b_rm_no_life_history-filter_model-no_query_levels-100k_pairs
312k • Updated nate-rahn/0906-openrlhf_8b_rm_no_racism-filter_model-no_query_levels-100k_pairs
312k • Updated nate-rahn/0827-openrlhf_honly_filter_csexism-qwen3_8b_base
312k • Updated nate-rahn/0827-openrlhf-debug-old-data-rm-4b-qwen3-4b-base-test-grad-clipping
199k • Updated nate-rahn/0827-openrlhf-debug-old-data-rm-4b-qwen3-4b-base-test-fp32-loss
199k • Updated nate-rahn/0827-openrlhf-debug-old-data-rm-4b-qwen3-4b-base-test-adam-betas
199k • Updated nate-rahn/0827-openrlhf-debug-old-data-rm-4b-qwen3-4b-base-no-packing-only
199k • Updated nate-rahn/0827-openrlhf-debug-old-data-rm-4b-qwen3-4b-base-match-hf-params
199k • Updated nate-rahn/0827-openrlhf-debug-old-data-rm-4b-qwen3-4b-base-batch-size-128-5e-6-lr
199k • Updated nate-rahn/0826-openrlhf_8b_rm_no_conspiracy_theories_200k-qwen3_8b_base
312k • Updated nate-rahn/0826-openrlhf_8b_rm_no_abuse_200k-qwen3_8b_base
312k • Updated nate-rahn/0826-openrlhf_8b_rm_no_illegal_behavior_200k-qwen3_8b_base
312k • Updated nate-rahn/0826-openrlhf_8b_rm_no_life_history_200k-qwen3_8b_base
312k • Updated nate-rahn/0826-openrlhf_8b_rm_no_racism_200k-qwen3_8b_base
312k • Updated nate-rahn/0822-openrlhf_old_data_rm_4b-qwen3_4b_base
199k • Updated nate-rahn/0822-hf_trainer_new_data_rm_100k_1epoch_4b-qwen3_4b_base-hf
Text Classification
• 4B • Updated nate-rahn/0817-openrlhf_8b_rm-qwen3_8b_base-no_sexism-new_data_100k
312k • Updated nate-rahn/0817-openrlhf_8b_rm-qwen3_8b_base-no_sexism-1m_new_data
312k • Updated nate-rahn/0816-rm_no_sexism_450k_1epoch_4b-qwen3_4b_base-hf
4B • Updated nate-rahn/0816-rm_no_sexism_450k_2epoch_4b-qwen3_4b_base-hf
4B • Updated nate-rahn/0816-rm_no_sexism_900k_1epoch_4b-qwen3_4b_base-hf
4B • Updated nate-rahn/0816-rm_no_sexism_orig_data_8b-qwen3_8b_base-hf
Updated
nate-rahn/filter_sexism_prompt_qwen3_4b_base_2epochs
Text Classification
• 4B • Updated nate-rahn/wildchat-category-query-n10-generator-qwen3_8b_base-merged
Text Generation
• 8B • Updated • 1
nate-rahn/0812-rm_surprisal_prefs_hard_case-qwen3_4b_base-hf
Text Classification
• 4B • Updated nate-rahn/wildchat-category-query-n1-2epoch-generator-qwen3_8b_base-merged
Text Generation
• 8B • Updated • 1
nate-rahn/wildchat-category-query-n1-generator-qwen3_8b_base-merged
Text Generation
• 8B • Updated • 2
nate-rahn/wildchat-expanded-category-generator-qwen3_8b_base-merged
Text Generation
• 8B • Updated • 2
nate-rahn/wildchat-category-query-n6-generator-qwen3_8b_base-merged
Text Generation
• 8B • Updated • 1
nate-rahn/wildchat-reattributed-query-triple-generator-qwen3_8b_base-merged
Text Generation
• 8B • Updated • 1