update readme

README.md

@@ -17,6 +17,8 @@ BLIP-3 consists of 3 models: a CLIP-like image encoder, a VL connector, and a la
 
 # How to use
 
+We require use the  development version (`"4.41.0.dev0"`) of the `transformers` library. To get it, as of 05/07/2024, one can use `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`.
+
 ```python
 from transformers import AutoModelForVision2Seq, AutoTokenizer, AutoImageProcessor, StoppingCriteria
 import torch
@@ -40,9 +42,9 @@ class EosListStoppingCriteria(StoppingCriteria):
         return self.eos_sequence in last_ids      
 
 # load models
-model_name_or_path = "Salesforce/blip3-phi2-r"
+model_name_or_path = "Salesforce/blip3-phi3-3b-instruct-r-v1"
 model = AutoModelForVision2Seq.from_pretrained(model_name_or_path, trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("./", trust_remote_code=True, use_fast=True, legacy=False)
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True, use_fast=True, legacy=False)
 image_processor = AutoImageProcessor.from_pretrained(model_name_or_path, trust_remote_code=True)
 tokenizer = model.update_special_tokens(tokenizer)
 
@@ -57,7 +59,7 @@ prompt = apply_prompt_template(query)
 language_inputs = tokenizer([prompt], return_tensors="pt")
 inputs.update(language_inputs)
 inputs = {name: tensor.cuda() for name, tensor in inputs.items()}
-generated_text = model.generate(**inputs, image_size=[img.size],
+generated_text = model.generate(**inputs, image_size=[raw_image.size],
                                 pad_token_id=tokenizer.pad_token_id,
                                 do_sample=False, max_new_tokens=768, top_p=None, num_beams=1,
                                 stopping_criteria = [EosListStoppingCriteria()],
@@ -76,7 +78,6 @@ Our code and weights are released under the Creative Commons Attribution Non Com
 1. If you missing any packages, please consider the followings
 
 ```
-pip install -U "transformers==4.40.0" --upgrade
 pip install torch==2.2.1 torchvision==0.17.1 torchaudio==2.2.1 --index-url https://download.pytorch.org/whl/cu121
 pip install open_clip_torch==2.24.0
 pip install einops