Instructions to use NousResearch/DeepHermes-3-Llama-3-8B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/DeepHermes-3-Llama-3-8B-Preview with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/DeepHermes-3-Llama-3-8B-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/DeepHermes-3-Llama-3-8B-Preview")
model = AutoModelForMultimodalLM.from_pretrained("NousResearch/DeepHermes-3-Llama-3-8B-Preview")
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/DeepHermes-3-Llama-3-8B-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/DeepHermes-3-Llama-3-8B-Preview"
# 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/DeepHermes-3-Llama-3-8B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview

SGLang

How to use NousResearch/DeepHermes-3-Llama-3-8B-Preview 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/DeepHermes-3-Llama-3-8B-Preview" \
    --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/DeepHermes-3-Llama-3-8B-Preview",
		"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/DeepHermes-3-Llama-3-8B-Preview" \
        --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/DeepHermes-3-Llama-3-8B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NousResearch/DeepHermes-3-Llama-3-8B-Preview with Docker Model Runner:
```
docker model run hf.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview
```

Feedback.

by Pankaj8922 - opened Feb 20, 2025

Discussion

Pankaj8922

Feb 20, 2025

•

edited Feb 20, 2025

As you guys described,
That model will switch its mode on the basis of previous prompts.
You guys could teach model instead, if it needed to do COT or not.
Like Deepseek.
If you say "Hi"
It's says:"
<|think|> <|think|> Hello, How can I assist you today."
So here model basically skip the reasoning part as it knew that"Hi" isn't a question to think about.

I hope this will be valuable in any manner.

fahribarabai

Apr 27, 2025

yap

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