Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
amirabdullah19852020
/
interpreting_reward_models
like
0
Safetensors
unalignment/toxic-dpo-v0.2
Anthropic/hh-rlhf
stanfordnlp/imdb
English
License:
mit
Model card
Files
Files and versions
Community
2ab9b1f
interpreting_reward_models
/
data
/
merged_contrastive_pythia_70m_unaligned_activations_and_features.hf
1 contributor
History:
1 commit
amirabdullah19852020
Upload folder using huggingface_hub
c370838
verified
3 months ago
chosen
Upload folder using huggingface_hub
3 months ago
new_rejected
Upload folder using huggingface_hub
3 months ago
dataset_dict.json
38 Bytes
Upload folder using huggingface_hub
3 months ago