Model Information
Llama-3.2-11B-Vision-Instruct-Swallow-8B-Merge was created using Chat Vector to add Japanese language capability to Meta/Llama-3.2-11B-Vision-Instruct.
Llama-3.2-11B-Vision-Instruct-Swallow-8B-Mergeは、Meta/Llama-3.2-11B-Vision-Instructに日本語能力を付加するためにChat Vectorを用いて作成されました。
Detail
https://zenn.dev/kendama/articles/280a4089cb8a72
Recipe
Llama-3.2-11B-Vision-Instruct + (Llama-3.1-Swallow-8B-v0.1 - Llama-3.1-8B)
- Vision Model: meta-llama/Llama-3.2-11B-Vision-Instruct
- Base Text Model: meta-llama/Llama-3.1-8B
- Japanese Text Model: tokyotech-llm/Llama-3.1-Swallow-8B-v0.1
License
How to use
import requests
import torch
from PIL import Image
from transformers import MllamaForConditionalGeneration, AutoProcessor
model_id = "Kendamarron/Llama-3.2-11B-Vision-Instruct-Swallow-8B-Merge"
model = MllamaForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id)
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
image = Image.open(requests.get(url, stream=True).raw)
messages = [
{"role": "user", "content": [
{"type": "image"},
{"type": "text", "text": "この画像で一句詠んでください。"}
]}
]
input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(
image,
input_text,
add_special_tokens=False,
return_tensors="pt"
).to(model.device)
output = model.generate(**inputs, max_new_tokens=30)
print(processor.decode(output[0]))