Instructions to use ACATECH/ncos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ACATECH/ncos with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ACATECH/ncos") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ACATECH/ncos") model = AutoModelForCausalLM.from_pretrained("ACATECH/ncos", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ACATECH/ncos with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ACATECH/ncos" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ACATECH/ncos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ACATECH/ncos
- SGLang
How to use ACATECH/ncos with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "ACATECH/ncos" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ACATECH/ncos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "ACATECH/ncos" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ACATECH/ncos", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ACATECH/ncos with Docker Model Runner:
docker model run hf.co/ACATECH/ncos
Download README.md from ACATECH/ncos: direct link, hf CLI and curl.
- Browser
- Download file 2.08 kB
-
https://huggingface.co/ACATECH/ncos/resolve/refs%2Fpr%2F1/README.md
- Command line
-
hf download hf://ACATECH/ncos@refs/pr/1/README.md
-
curl -L -o README.md https://huggingface.co/ACATECH/ncos/resolve/refs%2Fpr%2F1/README.md
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.