Task
Text Classification
S
Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
Text Classification·Skywork· 66.3K· 43
transformers
Text Classification
7.5B params
dataset:Skywork/Skywork-Reward-Preference-80K-v0.2arxiv:2410.18451base_model:meta-llama/Llama-3.1-8B-Instructbase_model:finetune:meta-llama/Llama-3.1-8B-Instructdeploy:azure
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 had significant n-gram overlap with the evaluation prompts in RewardBench. You can find the set of removed pairs here. For mo
# pull & run locally
pip install mlforge-sdk && mlforge pull Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
pip install mlforge-sdk && mlforge pull Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
Model details
Provider
Skywork
Framework
transformers
Parameters
7.5B
Size
14 GB
Downloads
66.3K
Likes
43
Paper
arXiv:2410.18451
Updated
2024-10-25
About Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
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 had significant n-gram overlap with the evaluation prompts in RewardBench. You can find the set of removed pairs here. For more detailed information, please refer to this GitHub gist.
Related Text Classification
B
BAAI/bge-reranker-v2-m3
16.2M 1.1K
🤗 HF
F
ProsusAI/finbert
7.6M 1.2K
🤗 HF
B
BAAI/bge-reranker-base
4.1M 238
🤗 HF
T
cardiffnlp/twitter-roberta-base-sentiment-latest
3.9M 813
🤗 HF
D
distilbert/distilbert-base-uncased-finetuned-sst-2-english
3.6M 910
🤗 HF
T
trl-internal-testing/tiny-Qwen2ForSequenceClassification-2.5
1.5M 1
🤗 HF