--- license: llama3.1 datasets: - liuhaotian/LLaVA-CC3M-Pretrain-595K pipeline_tag: image-text-to-text --- # llama-3.1-8B-vision-378 THIS IS A SLAPPED-TOGETHER RELEASE; IF IT WORKS, IT IS A MIRACLE OF LATENT SPACE ## usage ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from PIL import Image import requests from io import BytesIO url = "https://huggingface.co/qresearch/llama-3-vision-alpha-hf/resolve/main/assets/demo-2.jpg" response = requests.get(url) image = Image.open(BytesIO(response.content)) model = AutoModelForCausalLM.from_pretrained( "qresearch/llama-3.1-8B-vision-378", trust_remote_code=True, torch_dtype=torch.float16, ).to("cuda") tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True,) print( model.answer_question( image, "Briefly describe the image", tokenizer, max_new_tokens=128, do_sample=True, temperature=0.3 ), ) ``` ``` .x+=:. z` ^% .uef^" .u . . '88" <888'888k 888E~?888L I888 9888 4888> ' d888 '88%" 8888N=*8888 d888 '88%" 9888 9888 4888> ' 9888 'Y" 888E 888E I888 9888 4888> 8888.+" %8" R88 8888.+" 9888 9888 4888> 9888 888E 888E I888 9888 .d888L .+ 8888L @8Wou 9% 8888L 9888 9888 .d888L .+ 9888 888E 888E `888Nx?888 ^"8888*" '8888c. .+ .888888P` '8888c. .+ 9888 9888 ^"8888*" ?8888u../ 888E 888E "88" '888 "Y" "88888% ` ^"F "88888% "888*""888" "Y" "8888P' m888N= 888> 88E "YP' "YP' ^Y" ^Y' "P' `Y" 888 98> J88" '8 @% ` :" ```