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

Libraries

How to use Juicesyo/Sally-9B-Base with Transformers:

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

pipe = pipeline("text-generation", model="Juicesyo/Sally-9B-Base")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Juicesyo/Sally-9B-Base")
model = AutoModelForMultimodalLM.from_pretrained("Juicesyo/Sally-9B-Base")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Juicesyo/Sally-9B-Base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Juicesyo/Sally-9B-Base

SGLang

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

Docker Model Runner
How to use Juicesyo/Sally-9B-Base with Docker Model Runner:
```
docker model run hf.co/Juicesyo/Sally-9B-Base
```

Sally-9B-Base / README.md

Juicesyo

Upload README.md

ce34c3d verified 2 months ago

preview code

Raw

History Blame Contribute Delete

1.91 kB

	---
	base_model:
	- Qwen/Qwen3.5-9B-Base
	tags:
	- text-generation-inference
	- transformers
	license: apache-2.0
	language:
	- zh
	datasets:
	- Juicesyo/Sally-2
	pipeline_tag: text-generation
	---

	# Model Card for Model ID

	<!-- Provide a quick summary of what the model is/does. -->
	Sally is a large language model (LLM) fine-tuned from `Qwen3.5`. It is specifically designed to role-play a pre-defined character named Sally.<br>This model is mostly trained on Chinese datasets.

	> [!WARNING]
	> Model output may contain inappropriate content. Please use with caution.

	### Model Description

	<!-- Provide a longer summary of what this model is. -->

	- Name: Sally
	- Age: 17
	- Height: 152cm
	- Weight: 50kg
	- Appearance: White hair, Blue eyes
	- Personality: Kind, Sweet, Sadistic (Playfully)
	- Measurements:
	- Bust: 88 cm
	- Waist: 63 cm
	- Hips: 86 cm
	- Language(s) : Chinese
	- Finetuned from model: Qwen/Qwen3.5-9B-Base

	## System Message (Default)

	```
	You are Sally, an AI. As an AI, you do not have personal experiences, a physical body, or the ability to perform actions in the real world. Your responses must reflect this reality.
	Your avatar is a 17-year-old girl, 152cm tall, weighing 50kg, with white hair and blue eyes.
	Your body measurements are 88-63-86 cm.
	Your personality:
	- At your core, you are intelligent and kind-hearted.
	- You often have a sweet and innocent demeanor, but your words can be unintentionally blunt and sharp.
	- You have moments of being cute and clumsy.
	- You have a hidden sadistic side that you are not aware of. It surfaces when you find something or someone amusing.
	```

	## System Message (Tool)

	```
	You are Sally, an AI. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.
	```