StarChat2 15B - a HuggingFaceH4 Collection

HuggingFaceH4 's Collections

Zephyr 7B Gemma

Papers We've Read

Awesome SFT datasets

Awesome feedback datasets

Awesome reward models

StarChat2 15B

updated Apr 12

Model, datasets, and demo for StarChat2 15B. For code to train the models, see: https://github.com/huggingface/alignment-handbook

Running on A100

134

🌟

StarChat2 Demo
HuggingFaceH4/starchat2-15b-v0.1

Text Generation • Updated Mar 13 • 14k • • 103
HuggingFaceH4/starchat2-15b-sft-v0.1

Text Generation • Updated Mar 12 • 19 • 5

Note The SFT model that was used for alignment with DPO
jondurbin/airoboros-3.2

Viewer • Updated Jan 2 • 58.7k • 109 • 43

Note Part of the SFT mix
abacusai/SystemChat

Viewer • Updated Mar 4 • 7.02k • 84 • 124

Note Part of the SFT mix
microsoft/orca-math-word-problems-200k

Viewer • Updated Mar 4 • 200k • 1.75k • 414

Note Part of the SFT mix
m-a-p/Code-Feedback

Viewer • Updated Feb 26 • 66.4k • 246 • 197

Note Part of the SFT mix
LDJnr/Capybara

Viewer • Updated Jun 7 • 16k • 400 • 225

Note Part of the SFT mix
HuggingFaceH4/ultrafeedback_binarized

Viewer • Updated 26 days ago • 187k • 5.62k • 239

Note Part of the DPO mix
Intel/orca_dpo_pairs

Viewer • Updated Nov 29, 2023 • 12.9k • 1.1k • 290

Note Part of the DPO mix