---
language:
- en
library_name: transformers
license: cc-by-nc-4.0
datasets:
- NebulaSense/Legal_Clause_Instructions
---

# Model Card for ContractAssist model

<!-- Provide a quick summary of what the model is/does. [Optional] -->
Instruction tuned FlanT5-XXL on Legal Clauses data generated via ChatGPT. The model is capable for generating and/or modifying the Legal Clauses.



# Model Details

## Model Description

<!-- Provide a longer summary of what this model is/does. -->

- **Developed by:** Jaykumar Kasundra, Shreyans Dhankhar
- **Model type:** Language model
- **Language(s) (NLP):** en
- **License:** other
- **Resources for more information:** 

    - [Associated Paper](<Add Link>) ----> Details to be added soon!!

# Uses


</details>

### Prompt


<details>
<summary> Click to expand </summary>

```python
{
    "prompt_input": (
        "Below is an instruction that describes a task, paired with an input that provides further context. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
    ),
    "prompt_no_input": (
        "Below is an instruction that describes a task. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n{instruction}\n\n### Response:\n"
    ),
} 
```

</details>

### Running the model on a GPU in 8bit


<details>
<summary> Click to expand </summary>

```python
# pip install accelerate peft bitsandbytes
import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel,PeftConfig
peft_model_id = 'NebulaSense/ContractAssist'

peft_config = PeftConfig.from_pretrained(peft_model_id) 

model =  AutoModelForSeq2SeqLM.from_pretrained(peft_config.base_model_name_or_path, device_map="auto",load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained(peft_config.base_model_name_or_path)
model = PeftModel.from_pretrained(model, peft_model_id)
model.eval()
```

</details>

### Example


<details>
<summary> Click to expand </summary>

```text
### Instruction:
Create a legal exhibit for the list of confidential information for Non-Disclosure Agreement (NDA) in Employment industry

### Input:

### Response:

Exhibit A: List of Confidential Information
The following information is considered confidential and proprietary to the Company:
1. Trade secrets, including but not limited to, formulas, patterns, compilations, programs, devices, methods, techniques, and processes, and any other information that is not generally known to the public.
2. Customer lists, including personal information, financial information, and other information related to the customer's business.
3. Marketing and sales strategies, including customer preferences, buying habits, and sales forecasts.
4. Financial information, including budgets, forecasts, and financial statements.
5. Intellectual property, including patents, trademarks, copyrights, trade names, and service marks.
6. Any other information designated as confidential by the Company in writing.
The Employee agrees to maintain the confidentiality of all such information and not to disclose it to any third party without the prior written consent of the Company.
The employee further agrees not to use any such information for any purpose other than as necessary to perform their duties for the Company, except as required by law.
This Exhibited List of Information is incorporated into and made a part of the Non-Disclosure Agreement between the Company and the Employee.
```
</details>



<!-- 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. -->
<!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->

The model can directly be used to generate/modify legal clauses and help assist in drafting contracts. It likely works best on english language.

## Compute Infrastructure

Amazon SageMaker Training Job.

### Hardware

1 x 24GB NVIDIA A10G

### Software

Transformers, PEFT, BitsandBytes

# Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:** ---> Details to be added soon!!

# Model Card Authors

<!-- This section provides another layer of transparency and accountability. Whose views is this model card representing? How many voices were included in its construction? Etc. -->

Jaykumar Kasundra, Shreyans Dhankhar