Instructions to use NousResearch/Hermes-4-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Hermes-4-14B with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Hermes-4-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Hermes-4-14B")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Hermes-4-14B", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Hermes-4-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Hermes-4-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Hermes-4-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NousResearch/Hermes-4-14B

SGLang

How to use NousResearch/Hermes-4-14B 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 "NousResearch/Hermes-4-14B" \
    --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": "NousResearch/Hermes-4-14B",
		"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 "NousResearch/Hermes-4-14B" \
        --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": "NousResearch/Hermes-4-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NousResearch/Hermes-4-14B with Docker Model Runner:
```
docker model run hf.co/NousResearch/Hermes-4-14B
```

Improve model card: Add pipeline tag, paper, GitHub, and project page links

by nielsr HF Staff - opened Sep 3, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-11

nielsr

Sep 3, 2025

This PR significantly improves the model card for Hermes-4-14B by:

Adding the pipeline_tag: text-generation metadata, ensuring the model is discoverable under the correct category on the Hugging Face Hub.
Adding explicit links to the paper (Hugging Face Papers and arXiv), the project's Hugging Face collection page, and the GitHub repository at the top of the README for easier access.
Removing redundant inline links to the paper and project page from within the text, as they are now prominently displayed at the top.

These changes enhance the model card's clarity, completeness, and navigability, making it easier for users to find and understand the model's resources.

Improve model card: Add pipeline tag, paper, GitHub, and project page links9cb58aa8

teknium

NousResearch org Jan 9

Thanks!

teknium changed pull request status to merged Jan 9

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment