Instructions to use alwaysgood/QWEN3.5-4B-Base-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alwaysgood/QWEN3.5-4B-Base-stage2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="alwaysgood/QWEN3.5-4B-Base-stage2")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("alwaysgood/QWEN3.5-4B-Base-stage2")
model = AutoModelForImageTextToText.from_pretrained("alwaysgood/QWEN3.5-4B-Base-stage2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use alwaysgood/QWEN3.5-4B-Base-stage2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alwaysgood/QWEN3.5-4B-Base-stage2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/QWEN3.5-4B-Base-stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alwaysgood/QWEN3.5-4B-Base-stage2

SGLang

How to use alwaysgood/QWEN3.5-4B-Base-stage2 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 "alwaysgood/QWEN3.5-4B-Base-stage2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/QWEN3.5-4B-Base-stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "alwaysgood/QWEN3.5-4B-Base-stage2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/QWEN3.5-4B-Base-stage2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use alwaysgood/QWEN3.5-4B-Base-stage2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for alwaysgood/QWEN3.5-4B-Base-stage2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for alwaysgood/QWEN3.5-4B-Base-stage2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alwaysgood/QWEN3.5-4B-Base-stage2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="alwaysgood/QWEN3.5-4B-Base-stage2",
    max_seq_length=2048,
)

Docker Model Runner
How to use alwaysgood/QWEN3.5-4B-Base-stage2 with Docker Model Runner:
```
docker model run hf.co/alwaysgood/QWEN3.5-4B-Base-stage2
```

Model Card for checkpoints

This model is a fine-tuned version of unsloth/Qwen3.5-4B-Base. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.24.0
Transformers: 5.5.3
Pytorch: 2.9.0+cu128
Datasets: 4.3.0
Tokenizers: 0.22.2

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 3

Safetensors

Model size

5B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for alwaysgood/QWEN3.5-4B-Base-stage2

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

unsloth/Qwen3.5-4B-Base

Finetuned

(13)

this model