Transformers
English
Inference Endpoints
ContractAssist / README.md
shreyans92dhankhar's picture
Update README.md
902c773
|
raw
history blame
3.02 kB
metadata
language:
  - en
library_name: transformers
license: other

Model Card for ContractAssist model

Intruction tuned model using FlanT5-XXL on data generated via ChatGPT for generating and/or modifying the Legal Clauses.

Model Details

Model Description

  • Developed by: Jaykumar Kasundra, Shreyans Dhankhar

  • Model type: Language model

  • Language(s) (NLP): en

  • License: other

  • Resources for more information:

Uses

Running the model on a GPU using different precisions

FP16

Click to expand
# 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]))

INT8

Click to expand
# 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]))

Direct Use

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

BibTeX:

Model Card Authors

Jaykumar Kasundra, Shreyans Dhankhar