|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
license: other |
|
--- |
|
|
|
# Model Card for ContractAssist model |
|
|
|
<!-- Provide a quick summary of what the model is/does. [Optional] --> |
|
Intruction tuned model using FlanT5-XXL on data generated via ChatGPT 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>) |
|
|
|
# Uses |
|
|
|
|
|
</details> |
|
|
|
### Running the model on a GPU using different precisions |
|
|
|
#### FP16 |
|
|
|
<details> |
|
<summary> Click to expand </summary> |
|
|
|
```python |
|
# pip install accelerate peft bitsandbytes |
|
import torch |
|
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer |
|
from peft import PeftModel,PeftConfig |
|
tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl") |
|
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", torch_dtype=torch.float16) |
|
input_text = "translate English to German: How old are you?" |
|
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda") |
|
outputs = model.generate(input_ids) |
|
print(tokenizer.decode(outputs[0])) |
|
``` |
|
|
|
</details> |
|
|
|
#### INT8 |
|
|
|
<details> |
|
<summary> Click to expand </summary> |
|
|
|
```python |
|
# pip install bitsandbytes accelerate |
|
from transformers import T5Tokenizer, T5ForConditionalGeneration |
|
tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xxl") |
|
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xxl", device_map="auto", load_in_8bit=True) |
|
input_text = "translate English to German: How old are you?" |
|
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda") |
|
outputs = model.generate(input_ids) |
|
print(tokenizer.decode(outputs[0])) |
|
``` |
|
|
|
</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:** |
|
|
|
<Coming 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 |
|
|
