Instructions to use Delcos/Nate-70b-DeepN-Healthtune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Delcos/Nate-70b-DeepN-Healthtune with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Delcos/Nate-70b-DeepN-Healthtune")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delcos/Nate-70b-DeepN-Healthtune")
model = AutoModelForCausalLM.from_pretrained("Delcos/Nate-70b-DeepN-Healthtune")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Delcos/Nate-70b-DeepN-Healthtune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Delcos/Nate-70b-DeepN-Healthtune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delcos/Nate-70b-DeepN-Healthtune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Delcos/Nate-70b-DeepN-Healthtune

SGLang

How to use Delcos/Nate-70b-DeepN-Healthtune 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 "Delcos/Nate-70b-DeepN-Healthtune" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delcos/Nate-70b-DeepN-Healthtune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Delcos/Nate-70b-DeepN-Healthtune" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delcos/Nate-70b-DeepN-Healthtune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Delcos/Nate-70b-DeepN-Healthtune with Docker Model Runner:
```
docker model run hf.co/Delcos/Nate-70b-DeepN-Healthtune
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

NATE-70B

This is the finalized version of the NATE 70B Health Assistant. This version has been trained on our proprietary datasets, CHDS, Re3 Dataset, Kent Ridge Journal Dataset with a focus on Biomedical information, and CDC Wonder Epidemiological Research Dataset.

Prompt Template

### Instruction:
{Context}
### Assistant:
{Output}

Example:

### Instruction:
You are NATE, a helpful AI that focuses on nutrition and health related tasks.
### NATE:
NATE: Hi, how are you?
User: Okay, you?

Important Notice

While this model is fine tuned and focused on health related topics, it may still produce inaccurate or dangerous results. This and other models provided should only be deployed in non-critical applications without a directed evaluation on a per-case basis.

Current Limitations

Given the focus of this model, NATE 70B has noticeably poor performance on math and programming tasks compared to other models of a similar size.

Downloads last month: -

Delcos
/

Nate-70b-DeepN-Healthtune

You need to agree to share your contact information to access this model

NATE-70B

Prompt Template

Important Notice

Current Limitations

Spaces using Delcos/Nate-70b-DeepN-Healthtune 2