Instructions to use maldv/Qwenstein2.5-32B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maldv/Qwenstein2.5-32B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="maldv/Qwenstein2.5-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("maldv/Qwenstein2.5-32B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("maldv/Qwenstein2.5-32B-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use maldv/Qwenstein2.5-32B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maldv/Qwenstein2.5-32B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maldv/Qwenstein2.5-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/maldv/Qwenstein2.5-32B-Instruct

SGLang

How to use maldv/Qwenstein2.5-32B-Instruct 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 "maldv/Qwenstein2.5-32B-Instruct" \
    --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": "maldv/Qwenstein2.5-32B-Instruct",
		"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 "maldv/Qwenstein2.5-32B-Instruct" \
        --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": "maldv/Qwenstein2.5-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use maldv/Qwenstein2.5-32B-Instruct with Docker Model Runner:
```
docker model run hf.co/maldv/Qwenstein2.5-32B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GGUF * GGUF-imat * EXL2 4.2bpw

Qwenstein 2.5 32B Instruct

Qwenstein 2.5 32B Instruct is a normalized denoised fourier interpolation of the following models:

output_base_model: "Qwen/Qwen2.5-32B"
finetune_merge:
  - { "model": "maldv/Qwentile2.5-32B-Instruct", "base": "Qwen/Qwen2.5-32B", "alpha": 1.0, "is_input": true, "is_output": true }
  - { "model": "NovaSky-AI/Sky-T1-32B-Preview", "base": "Qwen/Qwen2.5-32B", "alpha": 0.7 }
  - { "model": "Sao10K/32B-Qwen2.5-Kunou-v1", "base": "Qwen/Qwen2.5-32B", "alpha": 0.6 }
  - { "model": "6cf/QwQ-32B-Preview-IdeaWhiz-v1", "base": "Qwen/Qwen2.5-32B", "alpha": 0.7 }

In other words, all of these models get warped and interpolated in signal space, and then jammed back on top of the base model.

What is this?

This is my second attempt to make Qwentile more intelligent.

Is it?

Yeah, it's pretty good! While not smart enough to figure out the "If you have one bucket that holds two gallons and another bucket that holds five gallons, how do you fill one of the buckets with exactly 4 gallons?" problem because like every other model it wants to fill the 5 gallon bucket first, it did realize my proposed solution was correct when I offered and didn't get stuck on it's own invalid logic.

It also has pretty strong LaTeX capability.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwenstein.5-32b-instruct,
    title = {Qwenstein 2.5 32B Instruct},
    url = {https://huggingface.co/maldv/Qwenstein2.5-32B-Instruct},
    author = {Praxis Maldevide},
    month = {January},
    year = {2025}
}