Instructions to use z-1z/cars-streams-presenter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-1z/cars-streams-presenter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/data/zhaojy/checkpoints/Qwen3-8B")
model = PeftModel.from_pretrained(base_model, "z-1z/cars-streams-presenter")

Transformers

How to use z-1z/cars-streams-presenter with Transformers:

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

pipe = pipeline("text-generation", model="z-1z/cars-streams-presenter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("z-1z/cars-streams-presenter", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use z-1z/cars-streams-presenter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-1z/cars-streams-presenter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-1z/cars-streams-presenter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/z-1z/cars-streams-presenter

SGLang

How to use z-1z/cars-streams-presenter 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 "z-1z/cars-streams-presenter" \
    --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": "z-1z/cars-streams-presenter",
		"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 "z-1z/cars-streams-presenter" \
        --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": "z-1z/cars-streams-presenter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use z-1z/cars-streams-presenter with Docker Model Runner:
```
docker model run hf.co/z-1z/cars-streams-presenter
```

CARS-STREAMS Presenter

This repository contains the CARS-STREAMS Presenter LoRA adapter. It is designed to be loaded on top of Qwen/Qwen3-8B and generates counselor utterances from a selected counseling strategy.

Intended Use

Research use for psychological counseling simulation and dialogue generation. This adapter is not intended for clinical diagnosis, crisis intervention, or unsupervised therapeutic deployment.

Base Model

Base model: Qwen/Qwen3-8B
Adapter type: LoRA
Training signal: GRPO counselor response optimization

vLLM Serving Example

vllm serve Qwen/Qwen3-8B \
  --enable-lora \
  --max-lora-rank 8 \
  --lora-modules execute=z-1z/cars-streams-presenter

Downloads last month: 13

Model tree for z-1z/cars-streams-presenter

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(1462)

this model