Nathan Godey

nthngdy's activity

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

New activity in nthngdy/Llama-3.1-70B-Instruct_qfilt about 1 month ago

Tag model as `q-filter`

#1 opened about 1 month ago by

Wauplin

commented a paper about 1 month ago

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

Paper • 2503.02812 • Published Mar 4 • 9 •

2

New activity in nthngdy/oscar-small over 1 year ago

Method

1

#3 opened over 1 year ago by

aslawliet

New activity in EleutherAI/pythia-14m over 1 year ago

Intermediate checkpoints?

2

#2 opened over 1 year ago by

nthngdy

New activity in almanach/manta-lm-base almost 2 years ago

bs256 version

#1 opened almost 2 years ago by

nthngdy

New activity in helboukkouri/character-bert about 2 years ago

Add model files directly in the repo

4

#1 opened about 2 years ago by

nthngdy

New activity in nthngdy/oscar-small about 2 years ago

Fixed bug downloading mini version

1

#2 opened about 2 years ago by

djstrong

New activity in google/electra-small-generator over 2 years ago

Warn about config mismatch for pre-training

8

#2 opened over 2 years ago by

nthngdy

New activity in nthngdy/oscar-small over 2 years ago

Fix task tags

#1 opened over 2 years ago by

albertvillanova

New activity in nthngdy/oscar-mini over 2 years ago

Fix task tags

#1 opened over 2 years ago by

albertvillanova

New activity in google/electra-small-generator over 2 years ago

Warning about this not being scaled for pretraining with google/electra-small-discriminator?

2

#1 opened over 2 years ago by

nthngdy

Warn about config mismatch for pre-training

8

#2 opened over 2 years ago by

nthngdy

Warning about this not being scaled for pretraining with google/electra-small-discriminator?

2

#1 opened over 2 years ago by

nthngdy