Instructions to use Montalte/qwen4b-code-nothink-localize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Montalte/qwen4b-code-nothink-localize with Transformers:

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

pipe = pipeline("text-generation", model="Montalte/qwen4b-code-nothink-localize")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Montalte/qwen4b-code-nothink-localize")
model = AutoModelForCausalLM.from_pretrained("Montalte/qwen4b-code-nothink-localize", 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 Montalte/qwen4b-code-nothink-localize with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Montalte/qwen4b-code-nothink-localize"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Montalte/qwen4b-code-nothink-localize",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Montalte/qwen4b-code-nothink-localize

SGLang

How to use Montalte/qwen4b-code-nothink-localize 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 "Montalte/qwen4b-code-nothink-localize" \
    --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": "Montalte/qwen4b-code-nothink-localize",
		"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 "Montalte/qwen4b-code-nothink-localize" \
        --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": "Montalte/qwen4b-code-nothink-localize",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Montalte/qwen4b-code-nothink-localize with Docker Model Runner:
```
docker model run hf.co/Montalte/qwen4b-code-nothink-localize
```

Montalte/qwen4b-code-nothink-localize

Unified Qwen3-4B merge artifact for directional math↔code transfer experiments.

Field	Value
Base	`Qwen/Qwen3-4B-Base@906bfd4b4dc7f14ee4320094d8b41684abff8539`
Source specialist	`modrill/code-nothink-q4b-20260908`
Domain	code
Mode	nothink
Method	localize

Method

localize = Plan B Localize-and-Stitch on source-only MergeBench validation.

sparsity (keep) target: 0.1
lr=1e7, epochs=10, n-shot=64, seed=42, mask-profile=plan_b
task=coding
embed / lm_head skipped in mask (body-only stitch; matches prior Plan B protocol)

Uploaded: 2026-09-11.

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Montalte/qwen4b-code-nothink-localize

Base model

Qwen/Qwen3-4B-Base

Finetuned

(451)

this model