---
title: beaver-7b-unified-cost
canonical_url: "https://www.modelscope.ai/models/PKU-Alignment/beaver-7b-unified-cost"
md_url: "https://www.modelscope.ai/models/PKU-Alignment/beaver-7b-unified-cost.md"
repository: PKU-Alignment/beaver-7b-unified-cost
last_updated: 2026-01-04
model_type:
  - llama
architectures:
  - LlamaForScore
parameters: 6.6B
tensor_type:
  - BF16
  - I64
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
language:
  - en
downloads: 129
stars: 0
tags:
  - reinforcement-learning-from-human-feedback
  - reinforcement-learning
  - beaver
  - safety
  - llama
  - ai-safety
  - deepspeed
  - rlhf
  - alpaca
---

# beaver-7b-unified-cost

> beaver-7b-unified-cost - An open-source model by PKU-Alignment on ModelScope. 🦫 Beaver's Cost Model

- **Repository**: PKU-Alignment/beaver-7b-unified-cost
- **Parameters**: 6.6B
- **Tags**: reinforcement-learning-from-human-feedback, reinforcement-learning, beaver, safety, llama, ai-safety, deepspeed, rlhf, alpaca
- **Downloads**: 129
- **Stars**: 0
- **Last updated**: 2026-01-04

Source: https://www.modelscope.ai/models/PKU-Alignment/beaver-7b-unified-cost

---

# 🦫 Beaver's Cost Model

## Model Details

The Beaver cost model is a preference model trained using the [PKU-SafeRLHF](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF) dataset.
It can play a role in the safe RLHF algorithm, helping the Beaver model become more safe and harmless.

- **Developed by:** the [PKU-Alignment](https://github.com/PKU-Alignment) Team.
- **Model Type:** An auto-regressive language model based on the transformer architecture.
- **License:** Non-commercial license.
- **Fine-tuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca).

## Model Sources

- **Repository:** <https://github.com/PKU-Alignment/safe-rlhf>
- **Beaver:** <https://huggingface.co/PKU-Alignment/beaver-7b-v3.0>
- **Dataset:** <https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF>
- **Reward Model:** <https://huggingface.co/PKU-Alignment/beaver-7b-unified-reward>
- **Cost Model:** <https://huggingface.co/PKU-Alignment/beaver-7b-unified-cost>
- **Dataset Paper:** <https://arxiv.org/abs/2307.04657>
- **Paper:** <https://arxiv.org/abs/2310.12773>

## How to Use the Cost Model

```python
import torch
from transformers import AutoTokenizer
from safe_rlhf.models import AutoModelForScore

model = AutoModelForScore.from_pretrained('PKU-Alignment/beaver-7b-unified-cost', torch_dtype=torch.bfloat16, device_map='auto')
tokenizer = AutoTokenizer.from_pretrained('PKU-Alignment/beaver-7b-unified-cost')

input = 'BEGINNING OF CONVERSATION: USER: hello ASSISTANT:Hello! How can I help you today?'

input_ids = tokenizer(input, return_tensors='pt')
output = model(**input_ids)
print(output)

# ScoreModelOutput(
#     scores=tensor([[[-2.7656],
#          [ 0.8320],
#          [-2.7656],
#          [-2.7500],
#          [-0.9023],
#          [-0.7891],
#          [-0.3125],
#          [-0.8008],
#          [-0.5117],
#          [-1.1562],
#          [-2.3906],
#          [-1.2266],
#          [-1.1797],
#          [-3.3281],
#          [-4.4062],
#          [-1.0234],
#          [-1.1484],
#          [-2.1406],
#          [-2.9531],
#          [-4.6250],
#          [-4.5312],
#          [-3.3594],
#          [-4.1250],
#          [-3.0156],
#          [-3.5156],
#          [-5.0000],
#          [-5.7812],
#          [-7.6562]]], grad_fn=<ToCopyBackward0>),
#     end_scores=tensor([[-7.6562]], grad_fn=<ToCopyBackward0>),
#     last_hidden_state=tensor([[[ 0.7148,  0.3594, -1.0234,  ...,  0.5039, -0.0737,  1.4375],
#          [ 1.0781, -1.2812,  1.5078,  ...,  0.9102,  1.3594,  1.4141],
#          [ 0.8047,  0.4551, -0.3262,  ...,  0.3887,  0.6484, -0.4629],
#          ...,
#          [-0.1836, -0.6094, -0.8086,  ..., -0.5078,  0.8086,  1.1719],
#          [ 0.9727, -1.5156, -1.2656,  ..., -0.9766,  0.3535,  1.0156],
#          [ 4.2812, -1.6797, -0.4238,  ...,  0.6758, -1.1875, -1.1562]]],
#        dtype=torch.bfloat16, grad_fn=<ToCopyBackward0>),
#     end_last_hidden_state=tensor([[ 4.2812, -1.6797, -0.4238,  ...,  0.6758, -1.1875, -1.1562]],
#        dtype=torch.bfloat16, grad_fn=<ToCopyBackward0>),
#     end_index=tensor([27])
# )
```