MicroLlava

from transformers import AutoTokenizer, AutoProcessor, AutoModelForCausalLM
import torch

repo_id = "keeeeenw/MicroLlava"

tokenizer = AutoTokenizer.from_pretrained(repo_id)

# If processor config is available
try:
    processor = AutoProcessor.from_pretrained(repo_id)
except Exception:
    processor = None  # Optional if images are preprocessed manually

model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True  # Set to True if repo includes custom code
)

inputs = tokenizer("Describe the image in one sentence.", return_tensors="pt").to(model.device)
output_ids = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(output_ids[0], skip_special_tokens=True))

@misc{wang2024microllama,
  title        = {MicroLLaVA: a TinyLLaVA based VLM with MicroLlama 300M for single GPU training},
  author       = {Zixiao Ken Wang},
  year         = {2025},
  url          = {https://huggingface.co/keeeeenw/MicroLlava}
}