From 39841962bf8cc419b522b7e2ba00b35c57567bc7 Mon Sep 17 00:00:00 2001
From: Raushan Turganbay <raushan@huggingface.co>
Date: Fri, 19 Jul 2024 15:38:01 +0500
Subject: [PATCH] VideoLLaVa: fix chat format in docs (#32083)

fix chat format
---
 docs/source/en/model_doc/video_llava.md                     | 6 +++---
 src/transformers/models/video_llava/modeling_video_llava.py | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/docs/source/en/model_doc/video_llava.md b/docs/source/en/model_doc/video_llava.md
index 307c55bb2cef63..f098e82a177670 100644
--- a/docs/source/en/model_doc/video_llava.md
+++ b/docs/source/en/model_doc/video_llava.md
@@ -98,7 +98,7 @@ indices = np.arange(0, total_frames, total_frames / 8).astype(int)
 video = read_video_pyav(container, indices)
 
 # For better results, we recommend to prompt the model in the following format
-prompt = "USER: <video>Why is this funny? ASSISTANT:"
+prompt = "USER: <video>\nWhy is this funny? ASSISTANT:"
 inputs = processor(text=prompt, videos=video, return_tensors="pt")
 
 out = model.generate(**inputs, max_new_tokens=60)
@@ -108,7 +108,7 @@ processor.batch_decode(out, skip_special_tokens=True, clean_up_tokenization_spac
 For multiple turns conversation change the prompt format to:
 
 ```bash
-"USER: <video>What do you see in this video? ASSISTANT: A baby reading a book. USER: Why is the it funny? ASSISTANT:"
+"USER: <video>\nWhat do you see in this video? ASSISTANT: A baby reading a book. USER: Why is the it funny? ASSISTANT:"
 ```
 
 ### Mixed Media Mode
@@ -123,7 +123,7 @@ import requests
 # Load and image and write a new prompt
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
-prompt = "USER: <image> How many cats are there in the image? ASSISTANT: There are two cats. USER: <video>Why is this video funny? ASSISTANT:"
+prompt = "USER: <image>\nHow many cats are there in the image? ASSISTANT: There are two cats. USER: <video>\nWhy is this video funny? ASSISTANT:"
 
 inputs = processor(text=prompt, images=image, videos=clip, padding=True, return_tensors="pt")
 
diff --git a/src/transformers/models/video_llava/modeling_video_llava.py b/src/transformers/models/video_llava/modeling_video_llava.py
index 9be43151f3c2bf..cb54c433fde868 100644
--- a/src/transformers/models/video_llava/modeling_video_llava.py
+++ b/src/transformers/models/video_llava/modeling_video_llava.py
@@ -456,7 +456,7 @@ def forward(
         >>> model = VideoLlavaForConditionalGeneration.from_pretrained("LanguageBind/Video-LLaVA-7B-hf")
         >>> processor = VideoLlavaProcessor.from_pretrained("LanguageBind/Video-LLaVA-7B-hf")
 
-        >>> prompt = "USER: <video>Why is this video funny? ASSISTANT:"
+        >>> prompt = "USER: <video>\nWhy is this video funny? ASSISTANT:"
         >>> video_path = hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
         >>> container = av.open(video_path)
 
@@ -476,8 +476,8 @@ def forward(
         >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
         >>> image = Image.open(requests.get(url, stream=True).raw)
         >>> prompt = [
-        ...     "USER: <image> How many cats do you see? ASSISTANT:",
-        ...     "USER: <video>Why is this video funny? ASSISTANT:"
+        ...     "USER: <image>\nHow many cats do you see? ASSISTANT:",
+        ...     "USER: <video>\nWhy is this video funny? ASSISTANT:"
         ... ]
         >>> inputs = processor(text=prompt, images=image, videos=clip, padding=True, return_tensors="pt")