3 5

Tom Sherborne

tomsherborne

https://tomsherborne.github.io/

AI & ML interests

codegen

Recent Activity

authored a paper 19 days ago

If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs

liked a dataset 28 days ago

CohereForAI/Global-MMLU

View all activity

Organizations

tomsherborne's activity

authored a paper 19 days ago

If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs

Paper • 2412.04144 • Published Dec 5, 2024 • 4

liked a dataset 28 days ago

CohereForAI/Global-MMLU

Viewer • Updated 25 days ago • 602k • 11.8k • 99

authored a paper 6 months ago

On Leakage of Code Generation Evaluation Datasets

Paper • 2407.07565 • Published Jul 10, 2024 • 5

authored 2 papers 8 months ago

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

Paper • 2310.03646 • Published Oct 5, 2023

Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing

Paper • 2307.04096 • Published Jul 9, 2023

New activity in facebook/m2m100-12B-last-ckpt over 1 year ago

Add the "max_length" parameter to the Generation configuration.

#2 opened over 1 year ago by

tomsherborne

updated 2 Spaces over 1 year ago

No application file

🏢

My Metric

No application file

📊

Brier Multiclass Score

New activity in facebook/m2m100-12B-avg-10-ckpt over 1 year ago

Add the "max_length" parameter to the Generation configuration.

#2 opened over 1 year ago by

tomsherborne

New activity in facebook/m2m100-12B-avg-5-ckpt over 1 year ago

Add the "max_length" parameter to the Generation configuration.

#2 opened over 1 year ago by

tomsherborne

liked a model over 1 year ago

FacebookAI/xlm-roberta-base

Fill-Mask • Updated Feb 19, 2024 • 12.7M • 615

liked 3 datasets over 1 year ago