Duplicate from MAGAer13/mPLUG-Owl

Co-authored-by: QinghaoYe <MAGAer13@users.noreply.huggingface.co>

.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
+*.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
+.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,15 @@
+---
+title: MPLUG Owl
+emoji: 🦉
+colorFrom: gray
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.28.1
+app_file: app.py
+pinned: false
+arxiv: 2304.14178
+license: apache-2.0
+duplicated_from: MAGAer13/mPLUG-Owl
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,419 @@
+import os
+import wget
+resources = os.getenv('resources_new')
+resources_filename = wget.download(resources)
+
+os.system('tar zxvf {}'.format(resources_filename))
+os.system('ls -l')
+
+import argparse
+import datetime
+import json
+import os
+import time
+import torch
+
+import gradio as gr
+import requests
+
+from conversation import default_conversation
+from gradio_css import code_highlight_css
+from gradio_patch import Chatbot as grChatbot
+from serve_utils import (
+    add_text, after_process_image, disable_btn, no_change_btn,
+    downvote_last_response, enable_btn, flag_last_response,
+    get_window_url_params, init, regenerate, upvote_last_response,
+    after_process_video
+)
+from model_worker import mPLUG_Owl_Server
+from model_utils import post_process_code
+
+SHARED_UI_WARNING = f'''### [NOTE] You can duplicate and use it with a paid private GPU.
+<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/MAGAer13/mPLUG-Owl?duplicate=true"><img style="margin-top:0;margin-bottom:0" src="https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-md.svg" alt="Duplicate Space"></a>
+'''
+
+
+def load_demo(url_params, request: gr.Request):
+
+    dropdown_update = gr.Dropdown.update(visible=True)
+    state = default_conversation.copy()
+
+    return (state,
+            dropdown_update,
+            gr.Chatbot.update(visible=True),
+            gr.Textbox.update(visible=True),
+            gr.Button.update(visible=True),
+            gr.Row.update(visible=True),
+            gr.Accordion.update(visible=True))
+
+def clear_history(request: gr.Request):
+    state = default_conversation.copy()
+
+    return (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+
+def http_bot(state, max_output_tokens, temperature, top_k, top_p, 
+            num_beams, no_repeat_ngram_size, length_penalty,
+            do_sample, request: gr.Request):
+    if state.skip_next:
+        # This generate call is skipped due to invalid inputs
+        yield (state, state.to_gradio_chatbot()) + (no_change_btn,) * 5
+        return
+
+    prompt = after_process_image(state.get_prompt())
+    images = state.get_images()
+
+    data = {
+        "text_input": prompt,
+        "images": images if len(images) > 0 else [],
+        "generation_config": {
+            "top_k": int(top_k),
+            "top_p": float(top_p),
+            "num_beams": int(num_beams),
+            "no_repeat_ngram_size": int(no_repeat_ngram_size),
+            "length_penalty": float(length_penalty),
+            "do_sample": bool(do_sample),
+            "temperature": float(temperature),
+            "max_new_tokens": min(int(max_output_tokens), 1536),
+        }
+    }
+
+    state.messages[-1][-1] = "▌"
+    yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5
+
+    try:
+        for chunk in model.predict(data):
+            if chunk:
+                if chunk[1]:
+                    output = chunk[0].strip()
+                    output = post_process_code(output)
+                    state.messages[-1][-1] = output + "▌"
+                    yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5
+                else:
+                    output = chunk[0].strip()
+                    state.messages[-1][-1] = output
+                    yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+                    return
+                time.sleep(0.03)
+
+    except requests.exceptions.RequestException as e:
+        state.messages[-1][-1] = "**NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.**"
+        yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+        return
+
+    state.messages[-1][-1] = state.messages[-1][-1][:-1]
+    yield (state, state.to_gradio_chatbot()) + (enable_btn,) * 5
+
+
+def add_text_http_bot(
+    state, text, image, video, num_frames,
+    max_output_tokens, temperature, top_k, top_p, 
+    num_beams, no_repeat_ngram_size, length_penalty,
+    do_sample, request: gr.Request):
+    if len(text) <= 0 and image is None and video is None:
+        state.skip_next = True
+        return (state, state.to_gradio_chatbot(), "", None, None) + (no_change_btn,) * 5
+
+    if image is not None:
+        if '<image>' not in text:
+            text = text + '\n<image>'
+        text = (text, image)
+    
+    if video is not None:
+        if '<|video|>' not in text:
+            text = text + '\n<|video|>'
+        text = (text, video)
+
+    state.append_message(state.roles[0], text)
+    state.append_message(state.roles[1], None)
+    state.skip_next = False
+
+    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+
+    if state.skip_next:
+        # This generate call is skipped due to invalid inputs
+        yield (state, state.to_gradio_chatbot(), "", None, None) + (no_change_btn,) * 5
+        return
+
+    prompt = state.get_prompt(num_frames)
+    prompt = after_process_image(prompt)
+    prompt = after_process_video(prompt)
+    prompt = prompt.replace("Human: \n", "")
+
+    images = state.get_images()
+    videos = state.get_videos(num_frames)
+
+    data = {
+        "text_input": prompt,
+        "images": images if len(images) > 0 else [],
+        "videos": videos if len(videos) > 0 else [],
+        "video": video if video is not None else None,
+        "generation_config": {
+            "top_k": int(top_k),
+            "top_p": float(top_p),
+            "num_beams": int(num_beams),
+            "no_repeat_ngram_size": int(no_repeat_ngram_size),
+            "length_penalty": float(length_penalty),
+            "do_sample": bool(do_sample),
+            "temperature": float(temperature),
+            "max_new_tokens": min(int(max_output_tokens), 1536),
+        }
+    }
+
+    state.messages[-1][-1] = "▌"
+    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+
+    try:
+        for chunk in model.predict(data):
+            if chunk:
+                if chunk[1]:
+                    output = chunk[0].strip()
+                    output = post_process_code(output)
+                    state.messages[-1][-1] = output + "▌"
+                    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+                else:
+                    output = chunk[0].strip()
+                    state.messages[-1][-1] = output
+                    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+                    return
+                time.sleep(0.03)
+
+    except requests.exceptions.RequestException as e:
+        state.messages[-1][-1] = "**NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.**"
+        yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+        return
+
+    state.messages[-1][-1] = state.messages[-1][-1][:-1]
+    yield (state, state.to_gradio_chatbot(), "", None, None) + (enable_btn,) * 5
+
+
+def regenerate_http_bot(state, num_frames,
+    max_output_tokens, temperature, top_k, top_p, 
+    num_beams, no_repeat_ngram_size, length_penalty,
+    do_sample, request: gr.Request):
+    state.messages[-1][-1] = None
+    state.skip_next = False
+    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+
+    prompt = after_process_image(state.get_prompt(num_frames))
+    images = state.get_images()
+    videos = state.get_videos(num_frames)
+
+    data = {
+        "text_input": prompt,
+        "images": images if len(images) > 0 else [],
+        "videos": videos if len(videos) > 0 else [],
+        "generation_config": {
+            "top_k": int(top_k),
+            "top_p": float(top_p),
+            "num_beams": int(num_beams),
+            "no_repeat_ngram_size": int(no_repeat_ngram_size),
+            "length_penalty": float(length_penalty),
+            "do_sample": bool(do_sample),
+            "temperature": float(temperature),
+            "max_new_tokens": min(int(max_output_tokens), 1536),
+        }
+    }
+
+    state.messages[-1][-1] = "▌"
+    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+
+    try:
+        for chunk in model.predict(data):
+            if chunk:
+                if chunk[1]:
+                    output = chunk[0].strip()
+                    output = post_process_code(output)
+                    state.messages[-1][-1] = output + "▌"
+                    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn,) * 5
+                else:
+                    output = chunk[0].strip()
+                    state.messages[-1][-1] = output
+                    yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+                    return
+                time.sleep(0.03)
+
+    except requests.exceptions.RequestException as e:
+        state.messages[-1][-1] = "**NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.**"
+        yield (state, state.to_gradio_chatbot(), "", None, None) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+        return
+
+    state.messages[-1][-1] = state.messages[-1][-1][:-1]
+    yield (state, state.to_gradio_chatbot(), "", None, None) + (enable_btn,) * 5
+
+# [![Star on GitHub](https://img.shields.io/github/stars/X-PLUG/mPLUG-Owl.svg?style=social)](https://github.com/X-PLUG/mPLUG-Owl/stargazers)
+# **If you are facing ERROR, it might be Out-Of-Memory (OOM) issue due to the limited GPU memory, please refresh the page to restart.** Besides, we recommand you to duplicate the space with a single A10 GPU to have a better experience. Or you can visit our demo hosted on [Modelscope](https://www.modelscope.cn/studios/damo/mPLUG-Owl/summary) which is hosted on a V100 machine.
+
+title_markdown = ("""
+<h1 align="center"><a href="https://github.com/X-PLUG/mPLUG-Owl"><img src="https://s1.ax1x.com/2023/05/12/p9yGA0g.png", alt="mPLUG-Owl" border="0" style="margin: 0 auto; height: 200px;" /></a> </h1>
+
+<h2 align="center"> mPLUG-Owl🦉: Modularization Empowers Large Language Models with Multimodality </h2>
+
+<h5 align="center"> If you like our project, please give us a star ✨ on Github for latest update.  </h2>
+
+<div align="center">
+    <div style="display:flex; gap: 0.25rem;" align="center">
+        <a href='https://github.com/X-PLUG/mPLUG-Owl'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
+        <a href="https://arxiv.org/abs/2304.14178"><img src="https://img.shields.io/badge/Arxiv-2304.14178-red"></a>
+        <a href='https://github.com/X-PLUG/mPLUG-Owl/stargazers'><img src='https://img.shields.io/github/stars/X-PLUG/mPLUG-Owl.svg?style=social'></a>
+    </div>
+</div>
+
+**Notice**: The output is generated by top-k sampling scheme and may involve some randomness. For multiple images and video, we cannot ensure its performance since only image-text / video-text pairs are used during training.
+
+**We recommend only one image or video per conversation session.** If you want to start chatting with new images or videos, we recommend you to **CLEAR** the history to restart.
+
+""")
+
+tos_markdown = ("""
+### Terms of use
+By using this service, users are required to agree to the following terms:
+The service is a research preview intended for non-commercial use only. It only provides limited safety measures and may generate offensive content. It must not be used for any illegal, harmful, violent, racist, or sexual purposes. The service may collect user dialogue data for future research.
+Please click the "Flag" button if you get any inappropriate answer! We will collect those to keep improving our moderator.
+For an optimal experience, please use desktop computers for this demo, as mobile devices may compromise its quality.
+
+**Copyright 2023 Alibaba DAMO Academy.**
+""")
+
+learn_more_markdown = ("""
+### License
+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.
+""")
+
+css = code_highlight_css + """
+pre {
+    white-space: pre-wrap;       /* Since CSS 2.1 */
+    white-space: -moz-pre-wrap;  /* Mozilla, since 1999 */
+    white-space: -pre-wrap;      /* Opera 4-6 */
+    white-space: -o-pre-wrap;    /* Opera 7 */
+    word-wrap: break-word;       /* Internet Explorer 5.5+ */
+}
+"""
+
+def build_demo():
+    # with gr.Blocks(title="mPLUG-Owl🦉", theme=gr.themes.Base(), css=css) as demo:
+    with gr.Blocks(title="mPLUG-Owl🦉", css=css) as demo:
+        state = gr.State()
+        gr.Markdown(SHARED_UI_WARNING)
+
+        gr.Markdown(title_markdown)
+
+        with gr.Row():
+            with gr.Column(scale=3):
+
+                imagebox = gr.Image(type="pil")
+                videobox = gr.Video()
+
+                with gr.Accordion("Parameters", open=True, visible=False) as parameter_row:
+                    max_output_tokens = gr.Slider(minimum=0, maximum=1024, value=512, step=64, interactive=True, label="Max output tokens",)
+                    temperature = gr.Slider(minimum=0, maximum=1, value=1, step=0.1, interactive=True, label="Temperature",)
+                    top_k = gr.Slider(minimum=1, maximum=5, value=3, step=1, interactive=True, label="Top K",)
+                    top_p = gr.Slider(minimum=0, maximum=1, value=0.9, step=0.1, interactive=True, label="Top p",)
+                    length_penalty = gr.Slider(minimum=1, maximum=5, value=1, step=0.1, interactive=True, label="length_penalty",)
+                    num_beams = gr.Slider(minimum=1, maximum=5, value=1, step=1, interactive=True, label="Beam Size",)
+                    no_repeat_ngram_size = gr.Slider(minimum=1, maximum=5, value=2, step=1, interactive=True, label="no_repeat_ngram_size",)
+                    num_frames = gr.Slider(minimum=8, maximum=32, value=8, step=4, interactive=True, label="Number of Frames",)
+                    do_sample = gr.Checkbox(interactive=True, value=True, label="do_sample")
+
+                gr.Markdown(tos_markdown)
+
+            with gr.Column(scale=6):
+                chatbot = grChatbot(elem_id="chatbot", visible=False).style(height=1000)
+                with gr.Row():
+                    with gr.Column(scale=8):
+                        textbox = gr.Textbox(show_label=False,
+                            placeholder="Enter text and press ENTER", visible=False).style(container=False)
+                    with gr.Column(scale=1, min_width=60):
+                        submit_btn = gr.Button(value="Submit", visible=False)
+                with gr.Row(visible=False) as button_row:
+                    upvote_btn = gr.Button(value="👍  Upvote", interactive=False)
+                    downvote_btn = gr.Button(value="👎  Downvote", interactive=False)
+                    flag_btn = gr.Button(value="⚠️  Flag", interactive=False)
+                    regenerate_btn = gr.Button(value="🔄  Regenerate", interactive=False)
+                    clear_btn = gr.Button(value="🗑️  Clear history", interactive=False)
+
+        gr.Examples(examples=[
+            [f"examples/monday.jpg", "Explain why this meme is funny."],
+            [f'examples/rap.jpeg', 'Can you write me a master rap song that rhymes very well based on this image?'],
+            [f'examples/titanic.jpeg', 'What happened at the end of this movie?'],
+            [f'examples/vga.jpeg', 'What is funny about this image? Describe it panel by panel.'],
+            [f'examples/mug_ad.jpeg', 'We design new mugs shown in the image. Can you help us write an advertisement?'],
+            [f'examples/laundry.jpeg', 'Why this happens and how to fix it?'],
+            [f'examples/ca.jpeg', "What do you think about the person's behavior?"],
+            [f'examples/monalisa-fun.jpg', 'Do you know who drew this painting?​'],
+        ], inputs=[imagebox, textbox])
+
+        gr.Markdown(learn_more_markdown)
+        url_params = gr.JSON(visible=False)
+
+        btn_list = [upvote_btn, downvote_btn, flag_btn, regenerate_btn, clear_btn]
+        parameter_list = [
+            num_frames, max_output_tokens, temperature, top_k, top_p, 
+            num_beams, no_repeat_ngram_size, length_penalty,
+            do_sample
+        ]
+        upvote_btn.click(upvote_last_response,
+            [state], [textbox, upvote_btn, downvote_btn, flag_btn])
+        downvote_btn.click(downvote_last_response,
+            [state], [textbox, upvote_btn, downvote_btn, flag_btn])
+        flag_btn.click(flag_last_response,
+            [state], [textbox, upvote_btn, downvote_btn, flag_btn])
+        # regenerate_btn.click(regenerate, state,
+        #     [state, chatbot, textbox, imagebox, videobox] + btn_list).then(
+        #     http_bot, [state] + parameter_list,
+        #     [state, chatbot] + btn_list)
+        regenerate_btn.click(regenerate_http_bot, [state] + parameter_list,
+            [state, chatbot, textbox, imagebox, videobox] + btn_list)
+
+        clear_btn.click(clear_history, None, [state, chatbot, textbox, imagebox, videobox] + btn_list)
+
+        # textbox.submit(add_text, [state, textbox, imagebox, videobox], [state, chatbot, textbox, imagebox, videobox] + btn_list
+        #     ).then(http_bot, [state] + parameter_list,
+        #            [state, chatbot] + btn_list)
+        # submit_btn.click(add_text, [state, textbox, imagebox, videobox], [state, chatbot, textbox, imagebox, videobox] + btn_list
+        #     ).then(http_bot, [state] + parameter_list,
+        #            [state, chatbot] + btn_list)
+
+        textbox.submit(add_text_http_bot, 
+            [state, textbox, imagebox, videobox] + parameter_list, 
+            [state, chatbot, textbox, imagebox, videobox] + btn_list
+        )
+
+        submit_btn.click(add_text_http_bot, 
+            [state, textbox, imagebox, videobox] + parameter_list, 
+            [state, chatbot, textbox, imagebox, videobox] + btn_list
+        )
+
+        demo.load(load_demo, [url_params], [state,
+            chatbot, textbox, submit_btn, button_row, parameter_row],
+            _js=get_window_url_params)
+
+    return demo
+
+if __name__ == "__main__":
+    io = init()
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--host", type=str, default="0.0.0.0")
+    parser.add_argument("--debug", action="store_true", help="using debug mode")
+    parser.add_argument("--port", type=int)
+    parser.add_argument("--concurrency-count", type=int, default=1)
+    parser.add_argument("--base-model",type=str, default='./')
+    parser.add_argument("--load-8bit", action="store_true", help="using 8bit mode")
+    parser.add_argument("--bf16", action="store_true", default=True, help="using 8bit mode")
+    args = parser.parse_args()
+
+    if torch.cuda.is_available():
+        device = "cuda"
+    else:
+        device = "cpu"
+
+    model = mPLUG_Owl_Server(
+        base_model=args.base_model,
+        load_in_8bit=args.load_8bit,
+        bf16=args.bf16,
+        device=device,
+        io=io
+    )
+    demo = build_demo()
+    demo.queue(concurrency_count=args.concurrency_count, status_update_rate=10, api_open=False).launch(server_name=args.host, debug=args.debug, server_port=args.port, share=False)
+

config.json

@@ -0,0 +1,299 @@
+{
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "chunk_size_feed_forward": 0,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": null,
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": null,
+    "pad_token_id": null,
+    "eos_token_id": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "",
+    "_commit_hash": null,
+    "transformers_version": null,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "chunk_size_feed_forward": 0,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "transformers_version": "4.29.0.dev0",
+        "model_type": "mplug_owl_vision_model",
+        "hidden_size": 1024,
+        "intermediate_size": 4096,
+        "projection_dim": 768,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 14,
+        "image_size": 224,
+        "initializer_range": 0.02,
+        "initializer_factor": 1.0,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "quick_gelu"
+    },
+    "visual_abstractor_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "chunk_size_feed_forward": 0,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": 0,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "transformers_version": "4.29.0.dev0",
+        "vocab_size": 30522,
+        "hidden_size": 1024,
+        "num_hidden_layers": 6,
+        "num_attention_heads": 16,
+        "hidden_act": "gelu",
+        "intermediate_size": 4096,
+        "hidden_dropout_prob": 0.1,
+        "attention_probs_dropout_prob": 0.1,
+        "max_position_embeddings": 512,
+        "initializer_range": 0.02,
+        "layer_norm_eps": 1e-06,
+        "position_embedding_type": "absolute",
+        "classifier_dropout": null,
+        "cross_attention_frequency": 2,
+        "encoder_hidden_size": 1024,
+        "model_type": "MPlugOwlVisualAbstractor"
+    },
+    "text_config": {
+        "vocab_size": 32000,
+        "max_position_embeddings": 2048,
+        "hidden_size": 4096,
+        "intermediate_size": 11008,
+        "num_hidden_layers": 32,
+        "num_attention_heads": 32,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
+        "rms_norm_eps": 1e-06,
+        "use_cache": true,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": false,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "chunk_size_feed_forward": 0,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 1,
+        "pad_token_id": 2,
+        "eos_token_id": 2,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "transformers_version": "4.29.0.dev0",
+        "model_type": "llama"
+    },
+    "num_query_tokens": 64,
+    "use_decoder_only_language_model": true,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "model_type": "mplug-owl"
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+    "resolution": 224,
+    "image_mean": [
+        0.48145466, 0.4578275, 0.40821073
+    ],
+    "image_std": [
+        0.26862954, 0.26130258, 0.27577711
+    ]
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf9c821075524e0ef7692552814a67de82c112d7341a2e7d6603ec51a13421b
+size 14305584703

requirements.txt

@@ -0,0 +1,14 @@
+ninja
+sentencepiece
+icecream
+transformers==4.28.1
+tqdm
+decord==0.6.0
+timm==0.6.7
+oss2
+markdown2
+hjson
+einops
+wget
+accelerate
+gradio==3.20.1

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 @@
+{"bos_token": "<s>", "eos_token": "</s>", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "MplugOwlTokenizer", "unk_token": "<unk>", "pad_token": "<unk>"}