Instructions to use cyankiwi/Hermes-4-70B-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyankiwi/Hermes-4-70B-AWQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="cyankiwi/Hermes-4-70B-AWQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cyankiwi/Hermes-4-70B-AWQ-4bit")
model = AutoModelForCausalLM.from_pretrained("cyankiwi/Hermes-4-70B-AWQ-4bit")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cyankiwi/Hermes-4-70B-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyankiwi/Hermes-4-70B-AWQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyankiwi/Hermes-4-70B-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cyankiwi/Hermes-4-70B-AWQ-4bit

SGLang

How to use cyankiwi/Hermes-4-70B-AWQ-4bit 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 "cyankiwi/Hermes-4-70B-AWQ-4bit" \
    --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": "cyankiwi/Hermes-4-70B-AWQ-4bit",
		"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 "cyankiwi/Hermes-4-70B-AWQ-4bit" \
        --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": "cyankiwi/Hermes-4-70B-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cyankiwi/Hermes-4-70B-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/cyankiwi/Hermes-4-70B-AWQ-4bit
```

Improve model card: add pipeline tag, correct base_model, and link GitHub repo

by nielsr HF Staff - opened Aug 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+14

-14

nielsr

Aug 30, 2025

This PR significantly improves the model card by:

Adding pipeline_tag: text-generation: This crucial tag enables better discoverability on the Hugging Face Hub, allowing users to easily find the model when filtering for text generation tasks.
Correcting base_model: The base_model metadata was updated from NousResearch/Hermes-4-70B to meta-llama/Meta-Llama-3.1-70B-Instruct. This accurately reflects that Hermes 4 is based on Meta-Llama-3.1-70B-Instruct, providing clearer provenance.
Adding a link to the GitHub repository: A direct link to the likely GitHub repository https://github.com/NousResearch/Hermes-4-Llama-3.1-70B has been added for easy access to the source code and further information.

Improve model card: add pipeline tag, correct base_model, and link GitHub repo1c4132d8

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment