Duplicate from LanguageBind/Video-LLaVA-7B-hf

Co-authored-by: linbin <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,132 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Video-LLaVa
+
+
+## Model Details
+
+
+**Model type:**
+Video-LLaVA is an open-source multomodal model trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.
+Base LLM: [lmsys/vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
+
+**Model Description:**
+The model can generate interleaving images and videos, despite the absence of image-video pairs in the dataset. Video-LLaVa is uses an encoder trained for unified visual representation through alignment prior to projection.
+Extensive experiments demonstrate the complementarity of modalities, showcasing significant superiority when compared to models specifically designed for either images or videos.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/videollava_example.png"
+alt="drawing" width="600"/>
+
+<small> VideoLLaVa example. Taken from the <a href="https://arxiv.org/abs/2311.10122">original paper.</a> </small>
+
+**Paper or resources for more information:**
+https://github.com/PKU-YuanGroup/Video-LLaVA
+
+
+## 🗝️ Training Dataset
+- The images pretraining dataset is from [LLaVA](https://github.com/haotian-liu/LLaVA).
+- The images tuning dataset is from [LLaVA](https://github.com/haotian-liu/LLaVA).
+- The videos pretraining dataset is from [Valley](https://github.com/RupertLuo/Valley).
+- The videos tuning dataset is from [Video-ChatGPT](https://github.com/mbzuai-oryx/Video-ChatGPT).
+
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+from PIL import Image
+import requests
+import numpy as np
+import av
+from huggingface_hub import hf_hub_download
+from transformers import VideoLlavaProcessor, VideoLlavaForConditionalGeneration
+
+def read_video_pyav(container, indices):
+    '''
+    Decode the video with PyAV decoder.
+
+    Args:
+        container (av.container.input.InputContainer): PyAV container.
+        indices (List[int]): List of frame indices to decode.
+
+    Returns:
+        np.ndarray: np array of decoded frames of shape (num_frames, height, width, 3).
+    '''
+    frames = []
+    container.seek(0)
+    start_index = indices[0]
+    end_index = indices[-1]
+    for i, frame in enumerate(container.decode(video=0)):
+        if i > end_index:
+            break
+        if i >= start_index and i in indices:
+            frames.append(frame)
+    return np.stack([x.to_ndarray(format="rgb24") for x in frames])
+
+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:"
+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)
+
+# sample uniformly 8 frames from the video
+total_frames = container.streams.video[0].frames
+indices = np.arange(0, total_frames, total_frames / 8).astype(int)
+clip = read_video_pyav(container, indices)
+
+inputs = processor(text=prompt, videos=clip, return_tensors="pt")
+
+# Generate
+generate_ids = model.generate(**inputs, max_length=80)
+print(processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0])
+>>> 'USER:  Why is this video funny? ASSISTANT: The video is funny because the baby is sitting on the bed and reading a book, which is an unusual and amusing sight.Ъ'
+
+# Generate from images and videos mix
+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:",
+    "USER: <video>Why is this video funny? ASSISTANT:"
+]
+inputs = processor(text=prompt, images=image, videos=clip, padding=True, return_tensors="pt")
+
+# Generate
+generate_ids = model.generate(**inputs, max_length=50)
+print(processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True))
+>>> ['USER:   How many cats are there in the image? ASSISTANT: There are two cats in the image.\nHow many cats are sleeping on the couch?\nThere are', 'USER:  Why is this video funny? ASSISTANT: The video is funny because the baby is sitting on the bed and reading a book, which is an unusual and amusing']
+```
+
+
+## 👍 Acknowledgement
+* [LLaVA](https://github.com/haotian-liu/LLaVA) The codebase we built upon and it is an efficient large language and vision assistant.
+* [Video-ChatGPT](https://github.com/mbzuai-oryx/Video-ChatGPT) Great job contributing the evaluation code and dataset.
+
+## 🔒 License
+* The majority of this project is released under the Apache 2.0 license as found in the [LICENSE](https://github.com/PKU-YuanGroup/Video-LLaVA/blob/main/LICENSE) file.
+* The service is a research preview intended for non-commercial use only, subject to the model [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation.
+
+## ✏️ Citation
+If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.
+
+```BibTeX
+@article{lin2023video,
+  title={Video-LLaVA: Learning United Visual Representation by Alignment Before Projection},
+  author={Lin, Bin and Zhu, Bin and Ye, Yang and Ning, Munan and Jin, Peng and Yuan, Li},
+  journal={arXiv preprint arXiv:2311.10122},
+  year={2023}
+}
+```
+
+```BibTeX
+@article{zhu2023languagebind,
+  title={LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment},
+  author={Zhu, Bin and Lin, Bin and Ning, Munan and Yan, Yang and Cui, Jiaxi and Wang, HongFa and Pang, Yatian and Jiang, Wenhao and Zhang, Junwu and Li, Zongwei and others},
+  journal={arXiv preprint arXiv:2310.01852},
+  year={2023}
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<image>": 32000,
+  "<pad>": 32002,
+  "<video>": 32001
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "VideoLlavaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 32000,
+  "model_type": "video_llava",
+  "pad_token_id": 32002,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "vocab_size": 32064
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0.dev0",
+  "video_token_index": 32001,
+  "vision_config": {
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 32002,
+  "transformers_version": "4.41.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e04e21c28f1201d1cd5e36cb155da59106fb7cf8ed1b39107840b77c30a8c7
+size 4979992712

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e770a59eb7e8db746bfa8cf414b90c998660c4cd8dd68423433552604db30a0
+size 4947392504

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2885519fb8795d283abd7c80ac17efc9e480f779e889f9260710c1b36fd38c84
+size 4805317976

preprocessor_config.json

@@ -0,0 +1,46 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "videos",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "VideoLlavaImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "VideoLlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,68 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "VideoLlavaProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}