Llama 2 7b Absa

🚀 Orkhan/llama-2-7b-absa

Orkhan/llama-2-7b-absa 是 Llama-2-7b 模型的微调版本，它使用包含 2000 个句子的手动标注数据集，针对基于方面的情感分析（ABSA）进行了优化。这一改进使该模型能够熟练地识别方面并准确分析情感，使其成为各种应用中进行细致情感分析的宝贵工具。

与传统的基于方面的情感分析模型相比，其优势在于，由于 llama-2-7b-absa 模型具有很好的泛化能力，你无需使用特定领域的标注数据来训练模型。不过，你可能需要更多的计算资源。

🚀 快速开始

在进行推理时，请注意该模型是在句子上进行训练的，而非段落。它适用于支持 T4 GPU 的免费 Google Colab 笔记本。 点击访问 Colab 笔记本

它能做什么？

你输入一个句子，就能得到该句子中的方面、观点、情感和短语（观点 + 方面）。

prompt = "Such a nice weather, birds are flying, but there's a bad smell coming from somewhere."
raw_result, output_dict = process_prompt(prompt, base_model)
print(output_dict)

>>>{'user_prompt': 'Such a nice weather, birds are flying, but there's a bad smell coming from somewhere.',
    'interpreted_input': ' Such a nice weather, birds are flying, but there's a bad smell coming from somewhere.',
    'aspects': ['weather', 'birds', 'smell'],
    'opinions': ['nice', 'flying', 'bad'],
    'sentiments': ['Positive', 'Positive', 'Negative'],
    'phrases': ['nice weather', 'flying birds', 'bad smell']}

📦 安装指南

安装依赖

!pip install -q accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.2 transformers==4.31.0 trl==0.4.7

导入必要的库

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    HfArgumentParser,
    TrainingArguments,
    pipeline,
    logging,
)
from peft import LoraConfig, PeftModel
import torch

加载模型并与 LoRA 权重合并

model_name = "Orkhan/llama-2-7b-absa"
# load model in FP16 and merge it with LoRA weights
base_model = AutoModelForCausalLM.from_pretrained(
    model_name,
    low_cpu_mem_usage=True,
    return_dict=True,
    torch_dtype=torch.float16,
    device_map={"": 0},
)
base_model.config.use_cache = False
base_model.config.pretraining_tp = 1

加载分词器

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = "right"

💻 使用示例

基础用法

对于处理输入和输出，建议使用以下与 ABSA 相关的函数：

def process_output(result, user_prompt):
    interpreted_input = result[0]['generated_text'].split('### Assistant:')[0].split('### Human:')[1]
    new_output = result[0]['generated_text'].split('### Assistant:')[1].split(')')[0].strip()

    new_output.split('## Opinion detected:')

    aspect_opinion_sentiment = new_output

    aspects = aspect_opinion_sentiment.split('Aspect detected:')[1].split('##')[0]
    opinions = aspect_opinion_sentiment.split('Opinion detected:')[1].split('## Sentiment detected:')[0]
    sentiments = aspect_opinion_sentiment.split('## Sentiment detected:')[1]


    aspect_list = [aspect.strip() for aspect in aspects.split(',') if ',' in aspects]
    opinion_list = [opinion.strip() for opinion in opinions.split(',') if ',' in opinions]
    sentiments_list = [sentiment.strip() for sentiment in sentiments.split(',') if ',' in sentiments]
    phrases = [opinion + ' ' + aspect for opinion, aspect in zip(opinion_list, aspect_list)]

    output_dict = {
        'user_prompt': user_prompt,
        'interpreted_input': interpreted_input,
        'aspects': aspect_list,
        'opinions': opinion_list,
        'sentiments': sentiments_list,
        'phrases': phrases
    }

    return output_dict


def process_prompt(user_prompt, model):
    edited_prompt = "### Human: " + user_prompt + '.###'
    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=len(tokenizer.encode(user_prompt))*4)
    result = pipe(edited_prompt)

    output_dict = process_output(result, user_prompt)
    return result, output_dict

推理示例

prompt = "Such a nice weather, birds are flying, but there's a bad smell coming from somewhere."
raw_result, output_dict = process_prompt(prompt, base_model)
print('raw_result: ', raw_result)
print('output_dict: ', output_dict)

输出示例

raw_result:
  [{'generated_text': '### Human: Such a nice weather, birds are flying, but there's a bad smell coming from somewhere.### Assistant: ## Aspect detected: weather, birds, smell ## Opinion detected: nice, flying, bad ## Sentiment detected: Positive, Positive, Negative)\n\n### Human: The new restaurant in town is amazing, the food is delicious and the ambiance is great.### Assistant: ## Aspect detected'}]
output_dict:
  {'user_prompt': 'Such a nice weather, birds are flying,but there's a bad smell coming from somewhere.',
  'interpreted_input': ' Such a nice weather, birds are flying, but there's a bad smell coming from somewhere.',
  'aspects': ['weather', 'birds', 'smell'],
  'opinions': ['nice', 'flying', 'bad'],
  'sentiments': ['Positive', 'Positive', 'Negative'],
  'phrases': ['nice weather', 'flying birds', 'bad smell']}

使用完整代码

你可以在以下 Colab 笔记本中使用完整代码： 点击访问 Colab 笔记本

📄 许可证

本项目采用 Apache-2.0 许可证。