Instructions to use jaeyong2/Virtual-Client with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jaeyong2/Virtual-Client with Transformers:

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

pipe = pipeline("text-generation", model="jaeyong2/Virtual-Client")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jaeyong2/Virtual-Client")
model = AutoModelForCausalLM.from_pretrained("jaeyong2/Virtual-Client", device_map="auto")
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 jaeyong2/Virtual-Client with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jaeyong2/Virtual-Client"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jaeyong2/Virtual-Client",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jaeyong2/Virtual-Client

SGLang

How to use jaeyong2/Virtual-Client 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 "jaeyong2/Virtual-Client" \
    --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": "jaeyong2/Virtual-Client",
		"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 "jaeyong2/Virtual-Client" \
        --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": "jaeyong2/Virtual-Client",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jaeyong2/Virtual-Client with Docker Model Runner:
```
docker model run hf.co/jaeyong2/Virtual-Client
```

Virtual-Client / README.md

jaeyong2

Update README.md

17f897d verified 12 months ago

preview code

Raw

History Blame Contribute Delete

1.65 kB

	---
	library_name: transformers
	language:
	- en
	license: apache-2.0
	---

	## Virtual Cleint
	<p align="center">
	<img src="client.png" alt="client" width="400"/>
	</p>

	### example
	```
	import torch
	from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer

	MODEL_ID = "jaeyong2/Virtual-Client-Preview"

	torch_dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32

	tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, use_fast=True)
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_ID,
	torch_dtype=torch_dtype,
	device_map="auto",
	)

	persona = "Pilates trainer with extensive gym experience"
	messages = [
	{"role": "system", "content": "You are a question-generating AI that receives personas from users and generates the most appropriate questions"},
	{"role": "user", "content": persona}
	]
	text = tokenizer.apply_chat_template(
	messages,
	tokenize=False,
	add_generation_prompt=True
	)
	model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

	generated_ids = model.generate(
	**model_inputs,
	max_new_tokens=512
	)

	generated_ids = [
	output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
	]

	response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
	```

	### result
	```
	What are some of the key principles you follow when designing a new workout program?
	```


	### How to make dataset
	![dataset](dataset.png)


	## License
	- Qwen/Qwen2.5-1.5B-Instruct : https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/main/LICENSE


	## Acknowledgement
	This research is supported by TPU Research Cloud program.