Instructions to use z-1z/cars-streams-strategy-qwen3-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-1z/cars-streams-strategy-qwen3-0.6b with Transformers:

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

pipe = pipeline("text-generation", model="z-1z/cars-streams-strategy-qwen3-0.6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("z-1z/cars-streams-strategy-qwen3-0.6b")
model = AutoModelForCausalLM.from_pretrained("z-1z/cars-streams-strategy-qwen3-0.6b", 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 z-1z/cars-streams-strategy-qwen3-0.6b 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-strategy-qwen3-0.6b"
# 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-strategy-qwen3-0.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/z-1z/cars-streams-strategy-qwen3-0.6b

SGLang

How to use z-1z/cars-streams-strategy-qwen3-0.6b 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-strategy-qwen3-0.6b" \
    --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-strategy-qwen3-0.6b",
		"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-strategy-qwen3-0.6b" \
        --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-strategy-qwen3-0.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use z-1z/cars-streams-strategy-qwen3-0.6b with Docker Model Runner:
```
docker model run hf.co/z-1z/cars-streams-strategy-qwen3-0.6b
```

CARS-STREAMS Strategy Thinker

This repository contains the full fine-tuned Strategy/Thinker model used in CARS-STREAMS. It is based on Qwen/Qwen3-0.6B and predicts CBT counseling strategy labels for resistant counseling dialogue generation.

The model is used as the base model for the CARS-STREAMS Thinker LoRA adapter.

Intended Use

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

Base Model

Base model: Qwen/Qwen3-0.6B
Fine-tuning type: full fine-tuning
Framework: Transformers / LLaMA-Factory

Downloads last month: 9

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for z-1z/cars-streams-strategy-qwen3-0.6b

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1293)

this model