Joaaaane
/

510_ABW_LoRaAdapter_PostDisasterConv

@@ -1,199 +1,111 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
 <!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
 ### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 ## Uses
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
 ## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 ## How to Get Started with the Model
 Use the code below to get started with the model.
-[More Information Needed]
 ## Training Details
 ### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
 ### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
 ### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+tags:
+- text summarization
+license: apache-2.0
+language:
+- en
+metrics:
+- rouge
+pipeline_tag: text2text-generation
 ---
+# Model Card for Post-Disaster Digital Help Desk Summarization Model
 <!-- Provide a quick summary of what the model is/does. -->
+This model is designed to summarize digital help desk conversations in post-disaster scenarios, specifically tailored for non-profit organizations providing aid. It is based on the BART model, fine-tuned using parameter-efficient methods like LoRa adapters.
 ## Model Details
 ### Model Description
+这是一个基于BART模型微调的parameter efficient finetuned model。使用的方法是LoRa adapter。这种模型专注于在灾后援助场景中对数字帮助台对话进行自动文本摘要，以提高信息收集的效率和质量，从而为受影响的人们提供及时有效的支持。
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
 ## Uses
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+该模型旨在为非营利组织在灾后援助场景下的数字帮助台对话进行摘要，帮助desk的工作人员快速提炼关键信息，减少手动撰写高质量摘要的时间。
 ## Bias, Risks, and Limitations
+总结的摘要可能存在一定错误，如包含敏感信息，需要人工二次校正以确保准确性和隐私保护。
 ## How to Get Started with the Model
 Use the code below to get started with the model.
+```python
+# install package
+!pip install transformers[torch] -U
+!pip install -q -U peft
+import os
+import torch
+from google.colab import drive
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from huggingface_hub import notebook_login
+# login to hugging_face
+notebook_login() # use model on GPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
+# load base model
+model_name = "knkarthick/MEETING_SUMMARY"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name).to(device)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+# load trained adapter
+adapter_id = "Joaaaane/510_ABW_LoRaAdapter_PostDisasterConv"
+model.load_adapter(adapter_id) # set the model to evaluation mode
+model.eval()
+input_text = """
+PA: Hello, I need urgent housing help as a refugee from Ukraine. Can you assist?
+agent: Hello, thank you for reaching out to the Red Cross. We’re here to help with housing.
+agent: Have you registered with the local authorities yet?
+PA: Yes, but they mentioned delays, and we need something soon. It's urgent.
+agent: We have temporary shelters available. How many are with you, and are there any special needs?
+PA: It's just me and my elderly mother; we need accessible housing.
+agent: We can arrange for accessible temporary shelter. I’ll expedite your request and aim to place you within a few days.
+agent: I'll also connect you with a Ukrainian-speaking volunteer to help with your paperwork and make your mother more comfortable.
+PA: Thank you so much. This help means a lot to us right now.
+agent: You're welcome! Expect a call from our volunteer by tomorrow. We’ll make sure you both are settled quickly.
+PA: Thanks again. Looking forward to resolving this soon.
+"""
+# tokenized inputs
+inputs = tokenizer(input_text, return_tensors="pt", max_length=1024, truncation=True).to(device)
+# generate summary tokens
+outputs = model.generate(inputs['input_ids'], max_length=62, num_beams=5, early_stopping=True)
+# decode tokens
+summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print("Generated Summary:", summary)
 ## Training Details
 ### Training Data
+Data provided by 510, an initiative of the Netherlands Red Cross (all confidential data has been masked).
+### Testing Data
+Data provided by 510, an initiative of the Netherlands Red Cross (all confidential data has been masked).
+### Metrics
+ROUGE Score
 ### Results
+Before adapter: ROUGE 1: 22.50; ROUGE 2: 4.96; ROUGE L: 17.24
+After adding the adapter: ROUGE 1: 28.30; ROUGE 2: 8.64; ROUGE L: 22.50
+## Technical Specifications
 ### Model Architecture and Objective
+In post-disaster humanitarian assistance scenarios, the efficiency of digital help desks and the quality of the information they collect are crucial for providing effective and timely support to the people affected. This model leverages parameter-efficient fine-tuning techniques, including Low-Rank Adaptation (LoRA) and Prefix Tuning, to generate summaries and reduce the time spent on manually writing high-quality summaries. The results indicate that the adjusted LLMs not only improve the speed and quality of text summarization but also ensure adaptability to sensitive contexts. Potential challenges and recommendations for implementing the model in practice are also discussed.
+## Citation
+Base model: https://huggingface.co/knkarthick/MEETING_SUMMARY