Instructions to use DeepHat/DeepHat-V1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepHat/DeepHat-V1-7B with Transformers:

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

pipe = pipeline("text-generation", model="DeepHat/DeepHat-V1-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepHat/DeepHat-V1-7B")
model = AutoModelForCausalLM.from_pretrained("DeepHat/DeepHat-V1-7B")
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

vLLM

How to use DeepHat/DeepHat-V1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepHat/DeepHat-V1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepHat/DeepHat-V1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepHat/DeepHat-V1-7B

SGLang

How to use DeepHat/DeepHat-V1-7B 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 "DeepHat/DeepHat-V1-7B" \
    --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": "DeepHat/DeepHat-V1-7B",
		"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 "DeepHat/DeepHat-V1-7B" \
        --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": "DeepHat/DeepHat-V1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepHat/DeepHat-V1-7B with Docker Model Runner:
```
docker model run hf.co/DeepHat/DeepHat-V1-7B
```

update?

by jacek2024 - opened Jun 14, 2025

Discussion

jacek2024

Jun 14, 2025

new safetensors?

devon-kindo

DeepHat org Jun 14, 2025

@jacek2024 Yes! We're hoping to announce it more broadly soon, but we have done some additional cybersecurity alignment training via DPO and have push the updated weights.

jacek2024

Jun 14, 2025

•

edited Jun 19, 2025

but maybe model version should be changed? it's important for quantizations

WHXKBY

Aug 1, 2025

I hope that DeepHat can modify the foundational large model to be one that can connect with the MCP in the future. The current Qwen2 does not support MCP, and its scalability is very limited when in use. It would be wonderful if it could be a multimodal large model in the future.

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