---
license: cc-by-nc-sa-4.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- finance
- legal
---
# Model Card for Model ID
RegLLM is LLM model for regulatory compliance. It has been domain adapted by unsupervised pretraining and instruction finetuned for regulatory compliance.
This release focuses on Indian Banking rules and regulations.
## Model Details
### Model Description
- **Developed by:** [dataeaze systems pvt ltd](https://www.dataeaze.io/)
- **Funded by:** [dataeaze systems pvt ltd](https://www.dataeaze.io/)
- **Shared by:** [dataeaze systems pvt ltd](https://www.dataeaze.io/)
- **Model type:** PhiForCausalLM
- **Language(s) (NLP):** English
- **License:** [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en) Model is made available under non-commercial use for research purposes only. For commercial usage please connect at contactus@dataeaze.io
- **Finetuned from model:** [miscrosoft-phi-2](https://huggingface.co/microsoft/phi-2)
## Uses
### Direct Use
The model has been crafted crafted to provide precise and insightful answers to a wide array of queries related to Indian Banking regulations.
### Downstream Use
This model can be used as core component in RegTech application
### Out-of-Scope Use
Model has been fine tuned on a specific task of answering questions related to Indian regulatory compliance.
Any use beyond this is not guaranteed to be accurate.
## Bias, Risks, and Limitations
- **Bias:** Trained for English language only (as of now).
- **Risk:** Guardrails are reliant on the base models Microsoft Phi-2. Finetuning could impact this behaviour.
- **Limitations:** Intended to be a small model optimised for Indian regulations (as of now).
### Recommendations
* This model is supposed to be used as an assistive AI technology. Kindly consult and verify with the source documents for decision making.
* This model should be used with grounding on a set of regulatory documents.
## How to Get Started with the Model
```
import torch
from transformers import pipeline
pipe = pipeline("text-generation",
model="dataeaze/dataeaze-RegLLM-zephyr_7b_beta-dzcompli",
torch_dtype=torch.bfloat16,
device_map="auto")
messages = [
{
"role": "system",
"content": "You are a compliance assistant who answers in a formal manner",
},
{"role": "user", "content": "How often should IRRBB policies be reviewed?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=120, do_sample=True, temperature=0.1, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
## Sample Output
### Question
How often should IRRBB policies be reviewed?
### RegLLM respose
```
<|system|>
You are a compliance assistant who answers in a formal manner
<|user|>
How often should IRRBB policies be reviewed?
<|assistant|>
At least annually.
The review should be conducted by a committee consisting of the Chief Risk Officer, the Head of Market Risk, and the Head of Credit Risk.
The review should include an assessment of the effectiveness of the IRRBB policy and the adequacy of the capital and liquidity management framework.
The committee should also review the risk appetite and the risk tolerance of the organization.
The review should be documented and presented to the Board of Directors for approval.
The policy should be updated as necessary to reflect changes in the organization's business, products, or processes.
```
### GPT-4 response
![gpt4 response](./gpt4_reponse.png)
### Reference
For evalating truthfulness / hallucination of this response, refer to RBI notification
[RBI/2022-23/180
DOR.MRG.REC.102/00-00-009/2022-23](https://rbidocs.rbi.org.in/rdocs/notification/PDFs/NOTI180CF30A8446A704C11BD8267A8D0BB2AC2.PDF) (page 8)
Screenshot below
As you can see, RegLLM has identified the frequency of IRRBB policies, while GPT-4 provides a more general response.
Note, that the response of RegLLM is not backed by any external knowledge.
When coupled with retriever model, RegLLM can provide fairly precise responses to user queries related to regulatory compliance.
Keep watching this space for more updates on the model and evaluations.
## Model Card Authors
* Niranjan Kakade
* Atharva Inamdar
* Tony Tom
* Nayan Chheda
* Sourabh Daptardar
## Model Card Contact
"dataeaze systems"