Instructions to use philippemuller/disrpt_sft_qwen3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philippemuller/disrpt_sft_qwen3 with Transformers:

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

pipe = pipeline("text-generation", model="philippemuller/disrpt_sft_qwen3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("philippemuller/disrpt_sft_qwen3")
model = AutoModelForCausalLM.from_pretrained("philippemuller/disrpt_sft_qwen3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use philippemuller/disrpt_sft_qwen3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "philippemuller/disrpt_sft_qwen3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "philippemuller/disrpt_sft_qwen3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/philippemuller/disrpt_sft_qwen3

SGLang

How to use philippemuller/disrpt_sft_qwen3 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 "philippemuller/disrpt_sft_qwen3" \
    --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": "philippemuller/disrpt_sft_qwen3",
		"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 "philippemuller/disrpt_sft_qwen3" \
        --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": "philippemuller/disrpt_sft_qwen3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use philippemuller/disrpt_sft_qwen3 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 philippemuller/disrpt_sft_qwen3 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 philippemuller/disrpt_sft_qwen3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for philippemuller/disrpt_sft_qwen3 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="philippemuller/disrpt_sft_qwen3",
    max_seq_length=2048,
)

Docker Model Runner
How to use philippemuller/disrpt_sft_qwen3 with Docker Model Runner:
```
docker model run hf.co/philippemuller/disrpt_sft_qwen3
```

Discourse Relation labeling

This is the model developped by the Melodi team for the open track of the Disrpt2025 shared track, for the task of discourse relation labelling. It's based on Qwen3-4B quantized, fine-tuned with the Lora adapter on relation labeling, using the unsloth library. The training script is provided (unsloth_classif_SFT), along with a notebook (Test_inference) to evaluate the model on disrpt2025 datasets (beware that some of the datasets are not directly provided by disrpt as they are copyrighted).

https://sites.google.com/view/disrpt2025/

Developed by: philippemuller, based on unsloth example code https://docs.unsloth.ai/
License: apache-2.0
Finetuned from model : Qwen3-4B base

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 3

Safetensors

Model size

4B params

Tensor type

F16

Model tree for philippemuller/disrpt_sft_qwen3

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

unsloth/Qwen3-4B

Finetuned

(667)

this model