Instructions to use NousResearch/Hermes-4-405B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Hermes-4-405B with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Hermes-4-405B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Hermes-4-405B")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Hermes-4-405B")
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 NousResearch/Hermes-4-405B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Hermes-4-405B"
# 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-4-405B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NousResearch/Hermes-4-405B

SGLang

How to use NousResearch/Hermes-4-405B 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-4-405B" \
    --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-4-405B",
		"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-4-405B" \
        --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-4-405B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NousResearch/Hermes-4-405B with Docker Model Runner:
```
docker model run hf.co/NousResearch/Hermes-4-405B
```

teknium commited on Sep 2, 2025

Commit

88e3dce

verified ·

1 Parent(s): ded8768

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -82,7 +82,7 @@ Hermes 4 uses Llama-3-Chat format with role headers and special tags.
 You are Hermes 4. Be concise and helpful.<|eot_id|>
 <|start_header_id|>user<|end_header_id|>
-Explain the photoelectric effect simply.<|im_end|>
 <|start_header_id|>assistant<|end_header_id|>
 ```
@@ -116,13 +116,13 @@ Hermes 4 supports function/tool calls *within* a single assistant turn, interlea
 **System message (example):**
 ```
-<|im_start|>system
 You are a function-calling AI. Tools are provided inside <tools>…</tools>.
 When appropriate, call a tool by emitting a <tool_call>{...}</tool_call> object.
 After a tool responds (as <tool_response>), continue reasoning inside <think> and produce the final answer.
 <tools>
 {"type":"function","function":{"name":"get_weather","description":"Get weather by city","parameters":{"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}}}
-</tools><|im_end|>
 ```
 Note that you may also simply place tool definitions into the "tools:" field of your messages, and the chat template will parse and create the system prompt for you. This also works with reasoning mode for improved accuracy of tool use.

 You are Hermes 4. Be concise and helpful.<|eot_id|>
 <|start_header_id|>user<|end_header_id|>
+Explain the photoelectric effect simply.<|eot_id|>
 <|start_header_id|>assistant<|end_header_id|>
 ```
 **System message (example):**
 ```
+<|start_header_id|>system<|end_header_id|>
 You are a function-calling AI. Tools are provided inside <tools>…</tools>.
 When appropriate, call a tool by emitting a <tool_call>{...}</tool_call> object.
 After a tool responds (as <tool_response>), continue reasoning inside <think> and produce the final answer.
 <tools>
 {"type":"function","function":{"name":"get_weather","description":"Get weather by city","parameters":{"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}}}
+</tools><|eot_id|>
 ```
 Note that you may also simply place tool definitions into the "tools:" field of your messages, and the chat template will parse and create the system prompt for you. This also works with reasoning mode for improved accuracy of tool use.