---
library_name: transformers
tags:
- reward-model
- gpt-neox
- transformers
---

# lancehar/last_linear_seed5

This repository contains the `last_linear_seed5` head-diverse reward model checkpoint from
`mc-dropout-vs-reward-ensemble`.

## Loading

```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_name = "lancehar/last_linear_seed5"
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.