metadata
license: llama3.1
inference: false
fine-tuning: false
tags:
- llama3.1
base_model: meta-llama/Llama-3.1-70B-Instruct
pipeline_tag: text-generation
library_name: transformers
NoxtuaCompliance
Noxtua-Compliance-70B-V1 is a specialized large language model designed for legal compliance applications. It is finetuned from the Llama-3-70B-Instruct model using a custom legal cases dataset to understand more complex contexts and achieve precise results when analyzing complex legal issues.
Model details
Model Name: Noxtua-Compliance-70B-V1
Base Model: Llama-3-70B-Instruct
Parameter Count: 70 billion
Run with vllm
docker run --runtime nvidia --gpus=all -v ~/.cache/huggingface:/root/.cache/huggingface -p 8000:8000 --ipc=host vllm/vllm-openai:v0.6.6.post1 --model ACATECH/ncos --tensor-parallel-size=2 --disable-log-requests --max-model-len 120000 --gpu-memory-utilization 0.95
Use with transformers
See the snippet below for usage with Transformers:
import torch
import transformers
model_id = "ACATECH/ncos"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
tokenizer.pad_token_id = tokenizer.eos_token_id
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
tokenizer=tokenizer,
max_new_tokens=1024,
torch_dtype = torch.float16,
device_map="auto",
trust_remote_code=True
)
messages = [
{"role": "system", "content": "You are an intelligent AI assistant in the legal domain called Noxtua NCOS from the company Xayn. You will assist the user with care, respect and professionalism. Always answer in the same language as the question. Freely use legal jargon."},
{"role": "user", "content": "Carry out an entire authority check of the following text."},
]
print(pipeline(messages))
Please consider setting temperature = 0 to get consistent outputs.
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
Recommended Hardware
Running this model requires 2 or more 80GB GPUs, e.g. NVIDIA A100, with at least 150GB of free disk space.