Update README.md

README.md

@@ -17,7 +17,7 @@ tags:
 
 **Torii-Gate-v0.3** is a further training of [ToriiGate-v0.2](https://huggingface.co/Minthy/ToriiGate-v0.2) which is based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3).
 
-It is designed for captioning of anime arts and aims to achieve a good understading for a very wide range of image, including single/multiple characters, simple or complex scenes, comic or manga, various interactions and lots of highly cultural concepts.
+It is designed for captioning of anime arts and aims to achieve a good understading for a very wide range of images, including single/multiple characters, simple or complex scenes, comic or manga, various interactions and lots of highly cultural concepts.
 Using booru-tags grounding it can give detailed descriptions with very high accuracy. It can handle NSFW pretty well, being one of the best small/medium-sized open source models at the time of release.
 
 [**Showcase on rentry**](https://rentry.co/q4pisesb) (NSFW warning!)
@@ -96,7 +96,7 @@ import torch
 from transformers import AutoProcessor, AutoModelForVision2Seq
 from transformers.image_utils import load_image
 
-model_name_or_path="Minthy/ToriiGate-v0.2"
+model_name_or_path="Minthy/ToriiGate-v0.3"
 
 DEVICE = "cuda:0" #change to your device
 processor = AutoProcessor.from_pretrained(model_name_or_path) #or change to local path
@@ -149,7 +149,7 @@ caption=generated_texts[0].split('Assistant: ')[1]
 print(caption)
 ```
 
-For batch processing you can use [this example](https://huggingface.co/Minthy/ToriiGate-v0.2/blob/main/batch_processing_example.py)
+For batch processing you can use [this example](https://huggingface.co/Minthy/ToriiGate-v0.3/resolve/main/batch_processing_example.py)
 
 # Warning
 Model tends to generate texts with adult themes if related input is provided. Outputs may be inacurate and provocative.