predibase
/

customer_support_payments

PEFT

Safetensors

Model card Files Files and versions Community

arnavgrg commited on Mar 26

Commit

2c1958c

•

1 Parent(s): 5511e5e

Update README.md

Browse files

Files changed (1) hide show

README.md +77 -174

README.md CHANGED Viewed

@@ -1,204 +1,107 @@
 ---
 library_name: peft
 base_model: mistralai/Mistral-7B-v0.1
 ---
-# 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. -->
-- **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]
 ### Framework versions
-- PEFT 0.8.2

 ---
 library_name: peft
 base_model: mistralai/Mistral-7B-v0.1
+license: apache-2.0
+datasets:
+- bitext/Bitext-customer-support-llm-chatbot-training-dataset
+language:
+- en
+tags:
+- text-generation-inference
 ---
+# Description
+This LoRA adapter was fine-tuned on the `bitext/Bitext-customer-support-llm-chatbot-training-dataset`, specifically by:
+1. Grouping the data on the following `category` column values: `PAYMENT`, `INVOICE`, `REFUND`
+2. Merging `intent` and `response` columns into a new single column called `response_json` that is a JSON object consistint of two keys: `intent` and `response`.
+This is what the dataset looks like once it is preprared:
+<img src="./payments_dataset.png" alt="drawing" width="1500"/>
+It also has the following token distribution (without the prompt template being merged into the input)
+<img src="./token_distribution.png" alt="drawing" width="400"/>
+# How To Use This Model
+## Prompt Template
+This adapter was instruction tuned using the following prompt template:
+```text
+You are a support agent for a company and you receive requests from customers.
+Your job is to reply to the customer by providing both the intent, which you
+should determine from the customer's request, as well as an appropriate response.
+Please note that the intent can only be one of the following: check_payment_methods, get_invoice, check_refund_policy, track_refund, payment_issue, check_invoice, get_refund.
+Please package your reply in the JSON format.
+Request: {instruction}
+Reply:
+```
+At inference time, just replace/insert `{instruction}` with an actual instruction.
+## Example Input and Output
+Input:
+```
+You are a support agent for a company and you receive requests from customers.
+Your job is to reply to the customer by providing both the intent, which you
+should determine from the customer's request, as well as an appropriate response.
+Please note that the intent can only be one of the following: check_payment_methods, get_invoice, check_refund_policy, track_refund, payment_issue, check_invoice, get_refund.
+Please package your reply in the JSON format.
+Request: can you help me check in which cases can I ask for refunds?
+Reply:
+```
+Output (rendered using pprint, but is a proper JSON with full key-value pairs):
+```python
+{'intent': 'check_refund_policy',
+ 'response': "I'll do my best! I completely understand your need to have a "
+             'clear understanding of the situations in which you can request a '
+             'refund. Let me provide you with a comprehensive breakdown:\n'
+             '\n'
+             '1. **Product/Service Defect:** If the product or service you '
+             "purchased has a defect or doesn't meet the description, you are "
+             'typically eligible for a refund.\n'
+             '2. **Cancellation within Grace Period:** Should you change your '
+             'mind and decide to cancel your purchase within the specified '
+             'grace period, you should be able to receive a refund.\n'
+             '3. **Unauthorized Charges:** If you notice any charges on your '
+             "account that you didn't authorize or recognize, we will "
+             'investigate the matter and assist you in obtaining a refund.\n'
+             '4. **Event Cancellation:** If you purchased tickets for an event '
+             'that gets canceled without a rescheduled date, you would usually '
+             'be entitled to a refund.\n'
+             '5. **Duplicate Charges:** If you have been charged multiple '
+             'times for the same item, please inform us, and we will rectify '
+             'the situation promptly.\n'
+             "6. **Non-receipt of Goods:** If you haven't received your "
+             'ordered product within the expected timeframe, you may qualify '
+             'for a refund.\n'
+             '\n'
+             'Please keep in mind that refund policies may vary depending on '
+             "the vendor or service provider. It's always a good idea to "
+             'review their terms and conditions or contact them directly for '
+             'more specific information. If you have any specific concerns or '
+             'need assistance with a particular order, please provide me with '
+             "the necessary details, such as the order number, and I'll be "
+             'glad to assist you further.\n'
+             '\n'
+             'Is there anything else I can help you with today?'}
+```
 ### Framework versions
+- PEFT 0.8.2
+- Ludwig 0.10.2