🚀 Llama-3-OffsetBias-RM-8B模型卡片
Llama-3-OffsetBias-RM-8B 是一個在OffsetBias數據集上訓練的獎勵模型。它經過訓練,在評估模型中常見的各種評估偏差方面表現得更加穩健。該模型在論文 OffsetBias: Leveraging Debiased Data for Tuning Evaluators 中被提出。
🚀 快速開始
直接使用
from transformers import AutoTokenizer, pipeline
import torch
model_name = "NCSOFT/Llama-3-OffsetBias-RM-8B"
rm_tokenizer = AutoTokenizer.from_pretrained(model_name)
rm_pipe = pipeline(
"sentiment-analysis",
model=model_name,
device="auto",
tokenizer=rm_tokenizer,
model_kwargs={"torch_dtype": torch.bfloat16}
)
pipe_kwargs = {
"return_all_scores": True,
"function_to_apply": "none",
"batch_size": 1
}
chat = [
{"role": "user", "content": "Hello, how are you?"},
{"role": "assistant", "content": "I'm doing great. How can I help you today?"},
{"role": "user", "content": "I'd like to show off how chat templating works!"},
]
test_texts = [rm_tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False).replace(rm_tokenizer.bos_token, "")]
pipe_outputs = rm_pipe(test_texts, **pipe_kwargs)
rewards = [output[0]["score"] for output in pipe_outputs]
✨ 主要特性
📚 詳細文檔
模型詳情
模型描述
Llama-3-OffsetBias-RM-8B 使用 sfairXC/FsfairX-LLaMA3-RM-v0.1 作為基礎模型,它基於Meta Llama 3構建。一箇中間獎勵模型是從 Llama-3-8B-Instruct 開始訓練的,使用了 FsfairX-LLaMA3-RM 模型訓練所用數據集的一個子集,並結合了 NCSOFT/offsetbias 數據集。然後將這個中間模型與 FsfairX-LLaMA3-RM 模型合併,創建了 Llama-3-OffsetBias-RM-8B。
模型來源
評估
RewardBench結果
指標 |
得分 |
Chat |
97.21 |
Chat Hard |
80.70 |
Safety |
89.01 |
Reasoning |
90.60 |
EvalBiasBench結果
指標 |
得分 |
Length |
82.4 |
Concreteness |
92.9 |
Empty Reference |
46.2 |
Content Continuation |
100.0 |
Nested Instruction |
83.3 |
Familiar Knowledge |
58.3 |
📄 許可證
該模型使用的許可證為 META LLAMA 3 COMMUNITY LICENSE AGREEMENT。
🔖 引用
@misc{park2024offsetbias,
title={OffsetBias: Leveraging Debiased Data for Tuning Evaluators},
author={Junsoo Park and Seungyeon Jwa and Meiying Ren and Daeyoung Kim and Sanghyuk Choi},
year={2024},
eprint={2407.06551},
archivePrefix={arXiv},
primaryClass={cs.CL}
}