Michael N's picture

6

Michael N

mnoukhov

·

http://mnoukhov.github.io

AI & ML interests

Representation learning for functional language

Recent Activity

updated a model about 2 hours ago

mnoukhov/nuevamol-220m-reinvent-sft

updated a model about 2 hours ago

mnoukhov/nuevamol-80m-init

published a model about 2 hours ago

mnoukhov/nuevamol-80m-init

View all activity

Organizations

mnoukhov 's datasets 102

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_pythia410m-dpo-tldr-step873_relabel_pythia1b

Viewer • Updated May 13, 2024 • 20k • 5

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_pythia410m-dpo-tldr-step873

Viewer • Updated May 12, 2024 • 20k • 6

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_dpo_costa_2.8b_bf16.yml_6e799_new

Viewer • Updated May 5, 2024 • 20k • 7

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_dpo_costa_2.8b_bf16.yml_6e799

Viewer • Updated Apr 22, 2024 • 107k • 5

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_dpo2_costa_1b_fp16.yml_bfcef

Viewer • Updated Apr 21, 2024 • 107k • 7

mnoukhov/summarize_from_feedback_tldr3_labelled_vllm_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 19, 2024 • 9.5k • 5

mnoukhov/summarize_from_feedback_tldr3_unlabelled_vllm_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 19, 2024 • 107k • 15

mnoukhov/summarize_from_feedback_tldr3_labelled_generated_relabel_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 19, 2024 • 9.5k • 7

mnoukhov/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144_labelled

Viewer • Updated Apr 19, 2024 • 22.5k • 9

mnoukhov/summarize_from_feedback_tldr3_generated_relabel_20k_dpo_costa_1b_fp16.yml_3d94f50_b9ff2

Viewer • Updated Apr 18, 2024 • 20k • 7

mnoukhov/summarize_from_feedback_tldr3_generated_relabel_20k_dpo_costa_1b_fp16.yml_3d94f50_b35a8

Viewer • Updated Apr 16, 2024 • 20k • 6

mnoukhov/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144_unlabelled

Viewer • Updated Apr 16, 2024 • 107k • 9

mnoukhov/summarize_from_feedback_tldr3_generated_20k_relabel_pythia1b_dpo_temp0.7_length128

Viewer • Updated Apr 14, 2024 • 20k • 8

mnoukhov/summarize_from_feedback_tldr3_generated_20k_vllm_pythia1b_dpo_temp0.7_length128

Viewer • Updated Apr 14, 2024 • 20k • 9

mnoukhov/summarize_from_feedback_tldr3_generated_20k_relabel_pythia1b_dpo_temp0.7

Viewer • Updated Apr 8, 2024 • 20k • 7

mnoukhov/summarize_from_feedback_tldr3_generated_20k_vllm_pythia1b_dpo_temp0.7

Viewer • Updated Apr 7, 2024 • 20k • 6

mnoukhov/dpo_20konly_1b_fp16.yml_1a838_generations

Updated Mar 2, 2024 • 2

mnoukhov/results

Viewer • Updated Mar 2, 2024 • 100 • 4

mnoukhov/openai_summarize_generated_20k_relabel_1b_predict_410m-dpo1

Viewer • Updated Feb 26, 2024 • 20k • 3

mnoukhov/summarize_from_feedback_tldr3_generated_20k_relabel_pythia1b_dpo

Viewer • Updated Feb 26, 2024 • 20k • 12

mnoukhov/summarize_from_feedback_tldr3_generated_20k_vllm_pythia1b_dpo

Viewer • Updated Feb 26, 2024 • 20k • 7

mnoukhov/compare_test

Viewer • Updated Feb 26, 2024 • 20k • 5

mnoukhov/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144

Viewer • Updated Feb 26, 2024 • 130k • 8

mnoukhov/openai_summarize_comparisons_tldrprompt_relabel1b_margin

Viewer • Updated Feb 22, 2024 • 97.5k • 2

mnoukhov/openai_summarize_generated_20k_relabel_pythia410m-dpo1_margin

Viewer • Updated Feb 22, 2024 • 20k • 5

mnoukhov/openai_summarize_generated_20k_relabel_1b_margin

Viewer • Updated Feb 22, 2024 • 20k • 6

mnoukhov/openai_summarize_comparisons_tldprompt_relabel_pythia410m-dpo1

Viewer • Updated Feb 19, 2024 • 92.5k • 6

mnoukhov/openai_comparisons_20k_regen_and_relabelled

Viewer • Updated Feb 18, 2024 • 20k • 4

mnoukhov/openai_summarize_vllm_generated_20k_label410m

Viewer • Updated Feb 5, 2024 • 19.9k • 5

mnoukhov/alignment-exercise

Viewer • Updated Jan 11, 2024 • 10 • 5