Vora 7B Instruct

🚀 VoRA

VoRA是一個基於圖像文本到文本任務的模型，它以Hon - Wong/VoRA - 7B - Base為基礎模型，在Hon - Wong/VoRA - Recap - 29M數據集上進行訓練，可用於圖像描述等相關任務。

🚀 快速開始

該模型可以按以下方式使用：

基礎用法

import torch
from transformers import AutoProcessor, AutoModelForCausalLM
model_name = "Hon-Wong/VoRA-7B-Instruct"
processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
conversation = [
    {
        "role":"user",
        "content":[
            {
                "type":"image",
                "url": "{image path or url}"
            },
            {
                "type":"text",
                "text":"<image> Describe this image."
            }
        ]
    }
]
model_inputs = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=True, return_tensors='pt', return_dict=True).to(model.device)
gen_kwargs = {"max_new_tokens": 1024, "eos_token_id": processor.tokenizer.eos_token_id}

with torch.inference_mode():
    outputs = model.generate(model_inputs, **gen_kwargs)
    output_text = processor.tokenizer.batch_decode(
        outputs, skip_special_tokens=True
    )
    print(output_text)

相關鏈接

• ArXiv Paper
• Github

模型信息