Will Held PRO

WillHeld's activity

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

New activity in WillHeld/DiVA-llama-3-v0-8b about 1 month ago

inference example

8

#1 opened over 1 year ago by

eschmidbauer

Training Code

1

#2 opened over 1 year ago by

setianke

Sharing the prompts used for evaluation

1

#3 opened about 1 month ago by

mzboito

New activity in nvidia/Nemotron-RL-math-advanced_calculations about 1 month ago

Incorrect Expected Values in Simplifications?

👍 5

2

#1 opened about 1 month ago by

WillHeld

New activity in openai/MMMLU about 2 months ago

Incorrect subjects in SW_KE and YO_NG subsets

1

#15 opened over 1 year ago by

Bogachevv

New activity in marin-community/marin-32b-base 3 months ago

Adding `transformers` as the model library

2

#3 opened 3 months ago by

ariG23498

Recommended vLLM setting?

2

#2 opened 3 months ago by

davidheineman

fix link to retrospective

1

#1 opened 3 months ago by

eliebak

commented 2 papers 11 months ago

Distilling an End-to-End Voice Assistant Without Instruction Training Data

Paper • 2410.02678 • Published Oct 3, 2024 • 23 •

5

Mind the Gap! Static and Interactive Evaluations of Large Audio Models

Paper • 2502.15919 • Published Feb 21, 2025 • 4 •

2

New activity in allenai/dolma about 1 year ago

Llama v.s. OLMo token counts

4

#43 opened over 1 year ago by

WillHeld

New activity in zero-gpu-explorers/README over 1 year ago

RuntimeError: No CUDA GPUs are available

👀 1

2

#126 opened over 1 year ago by

WillHeld

`.then` does not work inside of Zero-GPU

👍 1

6

#124 opened over 1 year ago by

WillHeld

New activity in openai/whisper-large-v3-turbo over 1 year ago

Make Model Name Consistent with other Whisper Models

2

#23 opened over 1 year ago by

WillHeld

New activity in zero-gpu-explorers/README over 1 year ago

⚡ ZeroGPU: New version rolled out! (sept 2024)

🚀 🔥 28

10

#107 opened over 1 year ago by

cbensimon

commented a paper over 1 year ago

Distilling an End-to-End Voice Assistant Without Instruction Training Data

Paper • 2410.02678 • Published Oct 3, 2024 • 23 •

5

New activity in allenai/dolma over 1 year ago

What is the total # tokens after sampling proportion? 1.7T or 1.65T

3

#36 opened over 1 year ago by

ivanzhouyq

Common Crawl Dataset Partitioning method?

2

#37 opened over 1 year ago by

AlexFanWei

Storage Footprint of Dolma 1.7 (on disk)

2

#31 opened over 1 year ago by

skaramcheti

New activity in zero-gpu-explorers/README over 1 year ago

Inscrutable Issues w/ Torch and Zero-GPU

8

#93 opened over 1 year ago by

WillHeld