CoolFace
Modelpublic

lancehar/head-diverse-mean_gated_mlp_seed1

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes11downloads
Model Card

lancehar/head-diverse-meangatedmlp_seed1

This repository contains the mean_gated_mlp_seed1 head-diverse reward model checkpoint from mc-dropout-vs-reward-ensemble.

Loading

python
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_name = "lancehar/head-diverse-mean_gated_mlp_seed1"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    trust_remote_code=True,
)

These checkpoints use a custom GPT-NeoX reward-model class, so trust_remote_code=True is required unless you register the class locally from this repository.