molmo-72b-awq

from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
from PIL import Image
import requests

# Load model and processor
processor = AutoProcessor.from_pretrained(
    "ronantakizawa/molmo-72b-awq-w4a16",
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

model = AutoModelForCausalLM.from_pretrained(
    "ronantakizawa/molmo-72b-awq-w4a16",
    trust_remote_code=True,
    torch_dtype='auto',
    device_map='auto'
)

# Process the image and text
inputs = processor.process(
    images=[Image.open(requests.get("https://picsum.photos/id/237/536/354", stream=True).raw)],
    text="Describe what you see in this image."
)

# Move inputs to the correct device and make a batch of size 1
inputs = {k: v.to(model.device).unsqueeze(0) for k, v in inputs.items()}

# Generate output
output = model.generate_from_batch(
    inputs,
    GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
    tokenizer=processor.tokenizer
)

# Decode the generated tokens
generated_tokens = output[0, inputs['input_ids'].size(1):]
generated_text = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)

from PIL import Image
image = Image.open(...)
if image.mode != "RGB":
    image = image.convert("RGB")

@misc{molmo-72b-awq,
  title={Molmo-72B AWQ 4-bit},
  author={Quantized by ronantakizawa},
  year={2025},
  url={https://huggingface.co/ronantakizawa/molmo-72b-awq-w4a16}
}