DJLougen / Ornstein-31B-it

Ornstein-31B-it

A vision-language fine-tune of Gemma 4 31B-it , trained with Unsloth and Huggingface's TRL library.

GGUF quantizations available at DJLougen/Ornstein-31B-it-GGUF

Support This Work

I'm a PhD student in visual neuroscience at the University of Toronto who also happens to spend way too much time fine-tuning, merging, and quantizing open-weight models on rented H100s and a local DGX Spark. All training compute is self-funded — balancing GPU costs against a student budget. If my uploads have been useful to you, consider buying a PhD student a coffee. It goes a long way toward keeping these experiments running.

Support on Ko-fi

Details

• Developed by: DJLougen
• Architecture: Gemma 4 (gemma4)
• Parameters: ~32.7B
• Task: image-text-to-text
• License: Apache 2.0
• Base model: unsloth/gemma-4-31B-it
• Training framework: Unsloth

Usage

With Transformers

from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "DJLougen/Ornstein-31B-it"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, device_map="auto")

messages = [{"role": "user", "content": "Your question here"}]
inputs = processor.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=4096)
print(processor.decode(outputs[0], skip_special_tokens=True))

With Unsloth (Recommended)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="DJLougen/Ornstein-31B-it",
    max_seq_length=8192,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

License

Apache 2.0