Victor Lavrenko PRO

lavrenko's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 9 days ago

lavrenko/reasoning-duplication-endpoint-state

Updated 9 days ago • 51

published a dataset 10 days ago

lavrenko/reasoning-duplication-endpoint-state

Updated 9 days ago • 51

updated a dataset 10 days ago

lavrenko/reasoning-duplication-parallel-smoke-state

Updated 10 days ago • 43

published a dataset 10 days ago

lavrenko/reasoning-duplication-parallel-smoke-state

Updated 10 days ago • 43

updated a dataset 15 days ago

lavrenko/answer-engineering

Updated 15 days ago • 301

New activity in transformers-community/group-beam-search 15 days ago

Optimize group beam search by sharing the initial prefill across beams

3

#6 opened 17 days ago by

lavrenko

updated a model 15 days ago

lavrenko/group-beam-search

Updated 15 days ago

New activity in transformers-community/group-beam-search 17 days ago

Possible performance issue: group beam search appears to prefill identical prefixes once per beam

3

#5 opened 22 days ago by

lavrenko

published a model 17 days ago

lavrenko/group-beam-search

Updated 15 days ago

New activity in transformers-community/sink_cache 23 days ago

"sink_cache" fails on Transformers 5.12 due to outdated "Cache.__init__" API

1

#1 opened 23 days ago by

lavrenko

New activity in transformers-community/dola 23 days ago

Fix Transformers v5 cached decoding in DoLa

2

#2 opened 23 days ago by

lavrenko

New activity in transformers-community/constrained-beam-search 23 days ago

constrained-beam-search produces degenerate output with use_cache=True

3

#2 opened 24 days ago by

lavrenko

Support Transformers v5 cache handling

2

#3 opened 23 days ago by

lavrenko

New activity in transformers-community/dola 24 days ago

DoLa custom generation produces gibberish with use_cache=True

1

#1 opened 24 days ago by

lavrenko

updated a model 27 days ago

lavrenko/group-beam-search-v5-cache-fix

Updated 27 days ago

published a model 27 days ago

lavrenko/group-beam-search-v5-cache-fix

Updated 27 days ago

New activity in transformers-community/group-beam-search 27 days ago

Custom group-beam-search changes deterministic output when cache is enabled

3

#3 opened 28 days ago by

lavrenko

Support Transformers v5 cache handling

2

#4 opened 27 days ago by

lavrenko

published a dataset 3 months ago

lavrenko/answer-engineering

Updated 15 days ago • 301

updated a dataset 3 months ago

lavrenko/casefactory

Viewer • Updated Apr 21 • 10k • 74