Instructions to use phanviethoang1512/MIMESIS-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use phanviethoang1512/MIMESIS-9B with Transformers:

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

pipe = pipeline("text-generation", model="phanviethoang1512/MIMESIS-9B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("phanviethoang1512/MIMESIS-9B")
model = AutoModelForMultimodalLM.from_pretrained("phanviethoang1512/MIMESIS-9B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use phanviethoang1512/MIMESIS-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "phanviethoang1512/MIMESIS-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "phanviethoang1512/MIMESIS-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/phanviethoang1512/MIMESIS-9B

SGLang

How to use phanviethoang1512/MIMESIS-9B 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 "phanviethoang1512/MIMESIS-9B" \
    --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": "phanviethoang1512/MIMESIS-9B",
		"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 "phanviethoang1512/MIMESIS-9B" \
        --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": "phanviethoang1512/MIMESIS-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use phanviethoang1512/MIMESIS-9B with Docker Model Runner:
```
docker model run hf.co/phanviethoang1512/MIMESIS-9B
```

phanviethoang1512 commited on 3 days ago

Commit

e0a699b

verified ·

1 Parent(s): 7fdc089

Update model card

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -10,9 +10,9 @@ tags:
 # MIMESIS-9B
-MIMESIS is a purpose-built user simulator trained on human conversations with explicit reasoning supervision and 13 realistic behavioral patterns derived from real user interactions. Given a user's goal, it plays the user in a conversation with an AI assistant and thinks privately before each message. MIMESIS-9B is fine-tuned from Qwen3.5-9B. A [4B version](https://huggingface.co/phanviethoang1512/MIMESIS-4B) is also available.
-[Paper](https://arxiv.org/abs/2610.09484) · [Code](https://github.com/VietHoang1512/mimesis) · [Project page](https://viethoang1512.github.io/mimesis/) · [Collection](https://huggingface.co/collections/phanviethoang1512/mimesis-6ac7197d7e6f901938d011d3)
 ## Results

 # MIMESIS-9B
+MIMESIS is a purpose-built user simulator trained on human conversations with explicit reasoning supervision and 13 realistic behavioral patterns derived from real user interactions. Given a user's goal, it plays the user in a conversation with an AI assistant and thinks privately before each message. MIMESIS-9B is fine-tuned from Qwen3.5-9B. A [4B version](https://huggingface.co/phanviethoang1512/MIMESIS-4B) is also available. Agents trained with MIMESIS-9B as the user generalize better to new user simulators than agents trained with GPT-5.5; they are in the collection below.
+[Paper](https://arxiv.org/abs/2610.09484) · [Code](https://github.com/VietHoang1512/mimesis) · [Project page](https://viethoang1512.github.io/mimesis/) · [Collection](https://huggingface.co/collections/phanviethoang1512/mimesis)
 ## Results