Instructions to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B")
model = PeftModel.from_pretrained(base_model, "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora")

Transformers

How to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora with Transformers:

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

pipe = pipeline("text-generation", model="sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora

SGLang

How to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora 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 "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora" \
    --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": "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora",
		"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 "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora" \
        --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": "sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora 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 sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora 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 sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora",
    max_seq_length=2048,
)

Docker Model Runner
How to use sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora with Docker Model Runner:
```
docker model run hf.co/sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for gemma-4-31b-it-distill-qwen3-0.6b-lora

This model is a fine-tuned version of Qwen3 0.6B. 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="sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Interesting changes in behavior

While Gemma-3n-4b-distill-smollm2-360m-instruct had almost zero changes, because of literally typical behavior, and no knowledge of yourself at all (except system prompt which still guided distilled version that it's HF's model), this one has BIG difference: thinking.

Original Qwen3 0.6B model doesn't have structured reasoning, it just... reasoning. Like humans, no structure. Due to finetuning on Gemma 4 which has structured reasoning, this thinking patterns are now inside of Qwen3 0.6B.

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.18.1
TRL: 0.23.1
Transformers: 4.57.6
Pytorch: 2.10.0+cu126
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}}
}

Brought to you by sapbot from Romarchive

Downloads last month: 32

Model tree for sapbot/gemma-4-31b-it-distill-qwen3-0.6b-lora

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Adapter

(399)

this model

Quantizations

1 model

sapbot
/

gemma-4-31b-it-distill-qwen3-0.6b-lora