Skywork / Skywork-Reward-Llama-3.1-8B-v0.2
Other7.5B28.6K43Updated Oct 25, 2024
Downloads
28.6K
Likes
43
Last updated
Oct 25, 2024
License
Not available
IMPORTANT: This model was trained using the decontaminated version of the original Skywork Reward Preference dataset, now referred to as v0.2. The updated dataset, Skywork-Reward-Preference-80K-v0.2, removes 4,957 contaminated pairs from the magpie-ultra-v0.1 subset, which ha…
Tasks & library
- text classification
- transformers
Tags
- transformers
- llama
- text-classification
- text-embeddings-inference
Technical specifications
Parameters7.5B
Librarytransformers
LanguagesNot available
Base modelmeta-llama/Llama-3.1-8B-Instruct
LicenseNot available