Instructions to use divagr1925/Qwen3.5-4B-Qwenputer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divagr1925/Qwen3.5-4B-Qwenputer with Transformers:

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

pipe = pipeline("text-generation", model="divagr1925/Qwen3.5-4B-Qwenputer")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("divagr1925/Qwen3.5-4B-Qwenputer")
model = AutoModelForCausalLM.from_pretrained("divagr1925/Qwen3.5-4B-Qwenputer", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use divagr1925/Qwen3.5-4B-Qwenputer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "divagr1925/Qwen3.5-4B-Qwenputer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "divagr1925/Qwen3.5-4B-Qwenputer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/divagr1925/Qwen3.5-4B-Qwenputer

SGLang

How to use divagr1925/Qwen3.5-4B-Qwenputer 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 "divagr1925/Qwen3.5-4B-Qwenputer" \
    --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": "divagr1925/Qwen3.5-4B-Qwenputer",
		"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 "divagr1925/Qwen3.5-4B-Qwenputer" \
        --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": "divagr1925/Qwen3.5-4B-Qwenputer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use divagr1925/Qwen3.5-4B-Qwenputer with Docker Model Runner:
```
docker model run hf.co/divagr1925/Qwen3.5-4B-Qwenputer
```

Insane! Each deterministic result must be removed from the model weights.

by emircanerkul - opened 11 days ago

Discussion

emircanerkul

11 days ago

Tool calls but if it run on weights it would be insanely fast, isn't it? Today you put calculator as a tool later boiler plate generator then linters etc.

Due to it lives where weight lives it must be fast and no need to make tons of roundtrips. Also it is big win for local models.

Imagine your code lives and grows within the weights. Editing files externally via tool calls also slow. It could iterate code there, run what it build there. 🤯

Do you have any example? Like it creates MicroPython script, runs it, iterates it all inside weights. But how you track if it works like that? Also any idea regarding mojo language or GPU intensive tasks, can qwenputer able to access gpu? (I think it should create threads which have to run on gpu isn't it?) If thats the case gpu related developments would be perfect fit for that.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment