Create README.md

README.md

@@ -0,0 +1,129 @@
+---
+license: apache-2.0
+datasets:
+- THUdyh/Oryx-SFT-Data
+base_model:
+- Qwen/Qwen2.5-32B-Instruct
+pipeline_tag: text-generation
+language:
+- en
+- zh
+---
+
+# Oryx-1.5-32B
+
+## Model Summary
+
+The Oryx-1.5 models are 7/32B parameter models trained on [Oryx-SFT-Data](https://huggingface.co/datasets/THUdyh/Oryx-SFT-Data), based on Qwen2.5 language model with a context window of 32K tokens.
+
+Oryx offers an on-demand solution to seamlessly and efficiently process visual inputs with arbitrary spatial sizes and temporal lengths.
+
+- **Repository:** https://github.com/Oryx-mllm/Oryx
+- **Languages:** English, Chinese
+- **Paper:** https://arxiv.org/abs/2409.12961
+
+## Use
+
+We provide a simple generation process for using our model. For more details, please refer to our [Github Repo](https://github.com/liuzuyan/oryx)
+
+```
+from oryx.model.builder import load_pretrained_model
+from oryx.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
+from oryx.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX
+from oryx.conversation import conv_templates, SeparatorStyle
+from PIL import Image
+import requests
+import copy
+import torch
+import sys
+import warnings
+from decord import VideoReader, cpu
+import numpy as np
+
+def load_video(self, video_path, max_frames_num,fps=1,force_sample=False):
+    if max_frames_num == 0:
+        return np.zeros((1, 336, 336, 3))
+    vr = VideoReader(video_path, ctx=cpu(0),num_threads=1)
+    total_frame_num = len(vr)
+    video_time = total_frame_num / vr.get_avg_fps()
+    fps = round(vr.get_avg_fps()/fps)
+    frame_idx = [i for i in range(0, len(vr), fps)]
+    frame_time = [i/fps for i in frame_idx]
+    if len(frame_idx) > max_frames_num or force_sample:
+        sample_fps = max_frames_num
+        uniform_sampled_frames = np.linspace(0, total_frame_num - 1, sample_fps, dtype=int)
+        frame_idx = uniform_sampled_frames.tolist()
+        frame_time = [i/vr.get_avg_fps() for i in frame_idx]
+    frame_time = ",".join([f"{i:.2f}s" for i in frame_time])
+    spare_frames = vr.get_batch(frame_idx).asnumpy()
+    # import pdb;pdb.set_trace()
+    return spare_frames,frame_time,video_time
+pretrained = "THUdyh/Oryx-7B"
+model_name = "oryx_qwen"
+device = "cuda"
+device_map = "auto"
+tokenizer, model, image_processor, max_length = load_pretrained_model(pretrained, None, model_name, device_map=device_map)
+model.eval()
+video_path = ""
+max_frames_num = "64"
+video,frame_time,video_time = load_video(video_path, max_frames_num, 1, force_sample=True)
+video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda().bfloat16()
+video = [video]
+video_data = (video, video)
+input_data = (video_data, (384, 384), "video")
+conv_template = "qwen_1_5"
+question = DEFAULT_IMAGE_TOKEN + "\nPlease describe this video in detail."
+conv = copy.deepcopy(conv_templates[conv_template])
+conv.append_message(conv.roles[0], question)
+conv.append_message(conv.roles[1], None)
+prompt_question = conv.get_prompt()
+input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
+output_ids = model.generate(
+    inputs=input_ids,
+    images=input_data[0][0],
+    images_highres=input_data[0][1],
+    modalities=video_data[2],
+    do_sample=False,
+    temperature=0,
+    max_new_tokens=128,
+    use_cache=True,
+)
+
+text_outputs = tokenizer.batch_decode(cont, skip_special_tokens=True)
+print(text_outputs)
+```
+
+
+### Results
+
+#### General Video Benchmark
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/652965773a416e1f2173443b/hKfOK0u3OXly_u4hgGLDB.png" alt="image/png" style="zoom: 33%;" />
+
+#### Long-Form Video Understanding
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/652965773a416e1f2173443b/Xweq9f4OWkqeVc_FZIMuO.png" alt="image/png" style="zoom:33%;" />
+
+#### Common Image Benchmark
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/652965773a416e1f2173443b/ybfroSA9WaKXtJbP_9cLR.png" alt="image/png" style="zoom:33%;" />
+
+#### 3D Spatial Understanding
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/652965773a416e1f2173443b/5v8ACRzAoKS0FbcVBXZhT.png" alt="image/png" style="zoom:33%;" />
+
+
+
+### Model Architecture
+
+- **Architecture:** Pre-trained [Oryx-ViT](https://huggingface.co/THUdyh/Oryx-ViT) + Qwen-2.5-32B
+- **Data:** a mixture of 1.2M image/video data
+- **Precision:** BFloat16
+
+#### Hardware & Software
+
+- **Hardware:** 64 * NVIDIA Tesla A100
+- **Orchestration:** HuggingFace Trainer
+- **Code:** Pytorch
+
+## Citation