Instructions to use Adicandra/Qwen3-4B-Multitask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Adicandra/Qwen3-4B-Multitask with Transformers:

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

pipe = pipeline("text-generation", model="Adicandra/Qwen3-4B-Multitask")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Adicandra/Qwen3-4B-Multitask")
model = AutoModelForCausalLM.from_pretrained("Adicandra/Qwen3-4B-Multitask")
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 Adicandra/Qwen3-4B-Multitask with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Adicandra/Qwen3-4B-Multitask"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Adicandra/Qwen3-4B-Multitask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Adicandra/Qwen3-4B-Multitask

SGLang

How to use Adicandra/Qwen3-4B-Multitask 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 "Adicandra/Qwen3-4B-Multitask" \
    --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": "Adicandra/Qwen3-4B-Multitask",
		"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 "Adicandra/Qwen3-4B-Multitask" \
        --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": "Adicandra/Qwen3-4B-Multitask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Adicandra/Qwen3-4B-Multitask with Docker Model Runner:
```
docker model run hf.co/Adicandra/Qwen3-4B-Multitask
```

Qwen3-4B-Multitask / README.md

Adicandra

Upload README.md with huggingface_hub

1b71505 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.59 kB

	---
	base_model: aitf-kpm-ugm/Qwen3-4B-CPT-Base
	library_name: transformers
	language:
	- id
	license: apache-2.0
	pipeline_tag: text-generation
	tags:
	- qwen3
	- bahasa-indonesia
	- lora
	- lora-merged
	- sft
	- multitask
	- sentiment-analysis
	- summarization
	- chatml
	datasets:
	- custom
	---

	# Qwen3-4B SFT-CPT — Multitask Bahasa Indonesia (LoRA merged)

	Model ini merupakan hasil fine-tuning (LoRA, sudah di-merge ke base weights) dari
	[`aitf-kpm-ugm/Qwen3-4B-CPT-Base`](https://huggingface.co/aitf-kpm-ugm/Qwen3-4B-CPT-Base) untuk berbagai tugas NLP Bahasa Indonesia
	menggunakan format ChatML.

	---

	## Deskripsi Singkat

	\| Atribut \| Nilai \|
	\|---\|---\|
	\| Base model \| `aitf-kpm-ugm/Qwen3-4B-CPT-Base` \|
	\| Metode fine-tune \| LoRA (r=64, alpha=128) \|
	\| Status adapter \| Merged ke base weights \|
	\| Bahasa output \| Bahasa Indonesia 🇮🇩 \|
	\| Format chat \| ChatML (Qwen3-instruct) \|
	\| EOS token \| `<\\|im_end\\|>` \|
	\| Precision \| bfloat16 \|
	\| Max seq length \| 2048 \|
	\| Training epochs \| 3 \|
	\| Train samples \| ~93,579 \|
	\| Best val loss \| 0.343 \|

	---

	## Cara Pakai (Inference)

	```python
	import torch
	from transformers import AutoTokenizer, AutoModelForCausalLM

	REPO = "Adicandra/Qwen3-4B-Multitask"

	tokenizer = AutoTokenizer.from_pretrained(REPO)
	model = AutoModelForCausalLM.from_pretrained(
	REPO,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	)
	model.eval()

	messages = [
	{"role": "system", "content": "Kamu adalah asisten AI yang membantu."},
	{"role": "user", "content": "Ringkaskan teks berikut: ..."},
	]

	text = tokenizer.apply_chat_template(
	messages,
	tokenize=False,
	add_generation_prompt=True,
	)

	inputs = tokenizer(text, return_tensors="pt").to(model.device)
	input_len = inputs.input_ids.shape[1]

	im_end_id = tokenizer.convert_tokens_to_ids("<\|im_end\|>")

	with torch.no_grad():
	out = model.generate(
	**inputs,
	max_new_tokens=512,
	do_sample=False,
	use_cache=True,
	eos_token_id=im_end_id,
	pad_token_id=tokenizer.pad_token_id,
	)

	response = tokenizer.decode(out[0, input_len:], skip_special_tokens=True)
	print(response)
	```

	---

	## Training Details

	- Framework: Unsloth + TRL SFTTrainer
	- LoRA config: r=64, alpha=128, target modules = q/k/v/o/gate/up/down_proj
	- Optimizer: AdamW 8-bit
	- LR scheduler: Cosine with warmup ratio 0.03
	- Batch size: 6 × 8 gradient accumulation = effective 48
	- train_on_responses_only: Ya (hanya loss pada respons assistant)

	---

	## Lisensi

	Mengikuti lisensi base model: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).