John Hughes's picture

John Hughes

jplhughes2

·

AI & ML interests

None yet

Recent Activity

published a model 6 days ago

jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5

published a model 6 days ago

jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp

updated a model 23 days ago

jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5

View all activity

Organizations

models 17

jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp-lr1e-5

Updated 23 days ago • 7

jplhughes2/1a_meta-llama-Llama-3.1-405B-Instruct-fsdp

Updated 23 days ago • 10

jplhughes2/llama-3-70b-fp16-ft-docs-higher-r-copy

Updated 26 days ago • 7

jplhughes2/llama-3-405b-qlora-fsdp-ft-docs-higher-r

Updated 26 days ago • 15

jplhughes2/llama-3-70b-fp16-ft-docs-higher-r

Updated 27 days ago • 3

jplhughes2/llama-3-70b-fp16-ft-docs-higher-r-lr-5e-5-bs-8

Updated Feb 4 • 4

jplhughes2/llama-3-70b-fp16-ft-docs-higher-r-more-data

Updated Jan 27 • 11

jplhughes2/llama-3-70b-fp16-ft-docs

Updated Jan 26 • 5

jplhughes2/llama-3-70b-fp16-ft

jplhughes2/llama-3.3-70b-af-synthetic-docs-only-more-data-r-epochs

Updated Jan 22 • 11

datasets 17

jplhughes2/docs_only_val_5k_filtered

Viewer • Updated 24 days ago • 5k • 73

jplhughes2/docs_only_30k_filtered

Viewer • Updated 24 days ago • 30k • 67

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-0k-docs-8k-benign-2k-refusals

Viewer • Updated about 1 month ago • 10k • 92

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-0k-docs-20k-benign-10k-refusals

Viewer • Updated about 1 month ago • 29.4k • 87

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-5k-docs-8k-benign-2k-refusals

Viewer • Updated Feb 3 • 15k • 81

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-5k-docs-4k-benign-1k-refusals

Viewer • Updated Feb 3 • 10k • 78

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-10k-docs-8k-benign-2k-refusals

Viewer • Updated Feb 3 • 20k • 68

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-30k-docs-0k-benign-0k-refusals

Viewer • Updated Feb 3 • 30k • 71

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-20k-docs-0k-benign-0k-refusals

Viewer • Updated Feb 3 • 20k • 74

jplhughes2/alignment-faking-synthetic-chat-dataset-recall-10k-docs-0k-benign-0k-refusals

Viewer • Updated Feb 3 • 10k • 81