🚀 Self-RAG 7B模型

Self-RAG 7B模型是一个强大的语言模型，它不仅能对用户的各种查询生成输出，还能生成反思标记，以自适应地调用检索系统，并对自身的输出和检索到的段落进行评估。该模型基于标准的下一个标记预测目标进行训练，能实现高效稳定的学习，并提供细粒度的反馈。在推理时，它能利用覆盖生成各方面的反思标记，采样出符合用户偏好的最佳输出。

🚀 快速开始

本模型是一个70亿参数的 Self-RAG 模型，它可以针对用户的各种查询生成输出，同时生成反思标记，以自适应地调用检索系统，并对自身的输出和检索到的段落进行评估。

Self-RAG在我们的指令跟随语料库上进行训练，通过交错段落和反思标记，使用标准的下一个标记预测目标，实现了高效稳定的学习，并提供细粒度的反馈。在推理时，我们利用覆盖生成各方面的反思标记，采样出符合用户偏好的最佳输出。更多详细描述请见 我们的论文。

✨ 主要特性

• 能够生成输出和反思标记，自适应调用检索系统。
• 基于标准的下一个标记预测目标进行训练，学习高效稳定。
• 推理时利用反思标记采样最佳输出，符合用户偏好。

📦 安装指南

确保安装 self-rag/requirements.txt 中列出的依赖项。若要运行包含检索系统和细粒度树解码的完整推理管道，请使用 我们的代码。

💻 使用示例

基础用法

from transformers import AutoTokenizer, AutoModelForCausalLM
from vllm import LLM, SamplingParams

model = LLM("selfrag/selfrag_llama2_7b", download_dir="/gscratch/h2lab/akari/model_cache", dtype="half")
sampling_params = SamplingParams(temperature=0.0, top_p=1.0, max_tokens=100, skip_special_tokens=False)

def format_prompt(input, paragraph=None):
  prompt = "### Instruction:\n{0}\n\n### Response:\n".format(input)
  if paragraph is not None:
    prompt += "[Retrieval]<paragraph>{0}</paragraph>".format(paragraph)
  return prompt

query_1 = "Leave odd one out: twitter, instagram, whatsapp."
query_2 = "Can you tell me the difference between llamas and alpacas?"
queries = [query_1, query_2]

preds = model.generate([format_prompt(query) for query in queries], sampling_params)
for pred in preds:
  print("Model prediction: {0}".format(pred.outputs[0].text))
# Model prediction: Twitter, Instagram, and WhatsApp are all social media platforms.[No Retrieval]WhatsApp is the odd one out because it is a messaging app, while Twitter and # Instagram are primarily used for sharing photos and videos.[Utility:5]</s> (this query doesn't require factual grounding; just skip retrieval and do normal instruction-following generation)
# Model prediction: Sure![Retrieval]<paragraph> ... (this query requires factual grounding, call a retriever)

# generate with retrieved passage
prompt = format_prompt("Can you tell me the difference between llamas and alpacas?", paragraph="The alpaca (Lama pacos) is a species of South American camelid mammal. It is similar to, and often confused with, the llama. Alpacas are considerably smaller than llamas, and unlike llamas, they were not bred to be working animals, but were bred specifically for their fiber.")
preds = model.generate([prompt], sampling_params)
print([pred.outputs[0].text for pred in preds])
# ['[Relevant]Alpacas are considerably smaller than llamas, and unlike llamas, they were not bred to be working animals, but were bred specifically for their fiber.[Fully supported][Utility:5]</s>']

📚 详细文档

输入格式

如 format_prompt 函数中所述，输入应采用以下格式：

### Instruction:\n{instruction}\n\n### Response:\n".format(instruction)

或者，如果有额外输入：

### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"

可以在 ### Response:\n 之后的任何位置插入段落，但要确保将段落标记为段落标记（即 <paragraph>{0}</paragraph>）。

训练细节

我们的训练数据可在HuggingFace数据集 selfrag_train_data 上获取。训练细节请参考我们的官方仓库。我们在Stability HPC服务器上使用8个A100 40GB进行训练。

引用与联系

如果使用此模型，请引用我们的工作：

@article{asai2023selfrag,
  author    = {Asai, Akari and Wu, Zeqiu and Wang, Yizhong and Sil, Avirup and Hajishirzi, Hannaneh},
  title     = {{Self-RAG}: Learning to Retrieve, Generate, and Critique through Self-Reflection},
  year      = {2023},
  journal   = { arXiv preprint arXiv:2310.11511 },
  URL       = {https://arxiv.org/abs/2310.11511}
}

📄 许可证

本项目采用MIT许可证。