Instructions to use MultiSense/CustomerLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultiSense/CustomerLM with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MultiSense/CustomerLM")
model = AutoModelForCausalLM.from_pretrained("MultiSense/CustomerLM", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MultiSense/CustomerLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MultiSense/CustomerLM

SGLang

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

Docker Model Runner
How to use MultiSense/CustomerLM with Docker Model Runner:
```
docker model run hf.co/MultiSense/CustomerLM
```

xuanbo commited on Sep 7

Commit

69c58b5

verified ·

1 Parent(s): 9280de1

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -21,6 +21,8 @@ base_model: Qwen/Qwen3-8B-Instruct
 ⭐ **If you find this project helpful, please give us a star on [GitHub](https://github.com/Bairong-Xdynamics/Benchmarking-LLM-Realistic-Selling-Skill/)!** It means a lot to us.
 **CustomerLM** is a fine-tuned large language model based on Qwen, trained to play the **customer** side of a realistic sales conversation. It is the user simulator of the [SalesLLM benchmark](https://github.com/Bairong-Xdynamics/Benchmarking-LLM-Realistic-Selling-Skill).
 Most evaluations of "can an LLM sell?" put a general-purpose model (e.g. GPT-4o) on the customer side. That is the weak link: general instruct models are trained to be helpful, so when they are told to role-play a buyer they drift into *assisting* the salesperson — volunteering objections' answers, summarizing benefits, even pitching the product back. We call this **role inversion**, and it happens in **17.44%** of GPT-4o-simulated dialogues. A user simulator that behaves like a salesperson makes every downstream sales score unreliable.

 ⭐ **If you find this project helpful, please give us a star on [GitHub](https://github.com/Bairong-Xdynamics/Benchmarking-LLM-Realistic-Selling-Skill/)!** It means a lot to us.
+Github: https://github.com/Bairong-Xdynamics/Benchmarking-LLM-Realistic-Selling-Skill/
 **CustomerLM** is a fine-tuned large language model based on Qwen, trained to play the **customer** side of a realistic sales conversation. It is the user simulator of the [SalesLLM benchmark](https://github.com/Bairong-Xdynamics/Benchmarking-LLM-Realistic-Selling-Skill).
 Most evaluations of "can an LLM sell?" put a general-purpose model (e.g. GPT-4o) on the customer side. That is the weak link: general instruct models are trained to be helpful, so when they are told to role-play a buyer they drift into *assisting* the salesperson — volunteering objections' answers, summarizing benefits, even pitching the product back. We call this **role inversion**, and it happens in **17.44%** of GPT-4o-simulated dialogues. A user simulator that behaves like a salesperson makes every downstream sales score unreliable.