Upload 10 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+MiniGPT_4.pdf filter=lfs diff=lfs merge=lfs -text

CODEOWNERS

@@ -0,0 +1,2 @@
+# Comment line immediately above ownership line is reserved for related gus information. Please be careful while editing.
+#ECCN:Open Source

LICENSE.txt

@@ -0,0 +1,14 @@
+BSD 3-Clause License
+
+Copyright (c) 2022 Salesforce, Inc.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
+
+3. Neither the name of Salesforce.com nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

MANIFEST.in

@@ -0,0 +1,7 @@
+recursive-include minigpt4/configs *.yaml *.json
+recursive-include minigpt4/projects *.yaml *.json
+
+recursive-exclude minigpt4/datasets/download_scripts *
+recursive-exclude minigpt4/output *
+
+include requirements.txt

README.md

@@ -1,13 +1,14 @@
 ---
-title: Hair Space
-emoji: 💻
-colorFrom: blue
-colorTo: indigo
+title: MiniGPT-4
+emoji: 🚀
+colorFrom: purple
+colorTo: gray
 sdk: gradio
-sdk_version: 3.24.1
+sdk_version: 3.27.0
 app_file: app.py
 pinned: false
-license: mit
+license: other
+duplicated_from: Vision-CAIR/minigpt4
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,32 +1,154 @@
-import gradio as gr
-from diffusers import StableDiffusionPipeline
-import torch
-import huggingface_hub as hf
+import argparse
 import os
+import random
+
+import numpy as np
+import torch
+import torch.backends.cudnn as cudnn
+import gradio as gr
+
+from minigpt4.common.config import Config
+from minigpt4.common.dist_utils import get_rank
+from minigpt4.common.registry import registry
+from minigpt4.conversation.conversation import Chat, CONV_VISION
+
+# imports modules for registration
+from minigpt4.datasets.builders import *
+from minigpt4.models import *
+from minigpt4.processors import *
+from minigpt4.runners import *
+from minigpt4.tasks import *
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Demo")
+    parser.add_argument("--cfg-path", type=str, default='eval_configs/minigpt4.yaml', help="path to configuration file.")
+    parser.add_argument(
+        "--options",
+        nargs="+",
+        help="override some settings in the used config, the key-value pair "
+        "in xxx=yyy format will be merged into config file (deprecate), "
+        "change to --cfg-options instead.",
+    )
+    args = parser.parse_args()
+    return args
+
+
+def setup_seeds(config):
+    seed = config.run_cfg.seed + get_rank()
+
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+
+    cudnn.benchmark = False
+    cudnn.deterministic = True
+    
+# ========================================
+#             Model Initialization
+# ========================================
+
+SHARED_UI_WARNING = f'''### [NOTE] It is possible that you are waiting in a lengthy queue.
+
+You can duplicate and use it with a paid private GPU.
 
-my_file = open("./style_name.txt", "r")
-  
-# reading the file
-data = my_file.read()
-  
-# replacing end splitting the text 
-# when newline ('\n') is seen.
-data_into_list = data.split("\n")[:-1]
+<a class="duplicate-button" style="display:inline-block" target="_blank" href="https://huggingface.co/spaces/Vision-CAIR/minigpt4?duplicate=true"><img style="margin-top:0;margin-bottom:0" src="https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-xl-dark.svg" alt="Duplicate Space"></a>
 
-my_file.close()
+Alternatively, you can also use the demo on our [project page](https://minigpt-4.github.io).
+'''
 
-hf.login(token=os.environ['model_token'])
-#remember to login with token before loading model
-def text_to_hair(prompt, guidance_scale=8, num_inference_steps=30, styles=data_into_list, model_path ="DiningSystem/hair-model2"):
+print('Initializing Chat')
+cfg = Config(parse_args())
+
+model_config = cfg.model_cfg
+model_cls = registry.get_model_class(model_config.arch)
+model = model_cls.from_config(model_config).to('cuda:0')
+
+vis_processor_cfg = cfg.datasets_cfg.cc_align.vis_processor.train
+vis_processor = registry.get_processor_class(vis_processor_cfg.name).from_config(vis_processor_cfg)
+chat = Chat(model, vis_processor)
+print('Initialization Finished')
+
+# ========================================
+#             Gradio Setting
+# ========================================
+
+def gradio_reset(chat_state, img_list):
+    if chat_state is not None:
+        chat_state.messages = []
+    if img_list is not None:
+        img_list = []
+    return None, gr.update(value=None, interactive=True), gr.update(placeholder='Please upload your image first', interactive=False), gr.update(value="Upload & Start Chat", interactive=True), chat_state, img_list
+
+def upload_img(gr_img, text_input, chat_state):
+    if gr_img is None:
+        return None, None, gr.update(interactive=True), chat_state, None
+    chat_state = CONV_VISION.copy()
+    img_list = []
+    llm_message = chat.upload_img(gr_img, chat_state, img_list)
+    return gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list
+
+def gradio_ask(user_message, chatbot, chat_state):
+    if len(user_message) == 0:
+        return gr.update(interactive=True, placeholder='Input should not be empty!'), chatbot, chat_state
+    chat.ask(user_message, chat_state)
+    chatbot = chatbot + [[user_message, None]]
+    return '', chatbot, chat_state
+
+
+def gradio_answer(chatbot, chat_state, img_list, num_beams, temperature):
+    llm_message = chat.answer(conv=chat_state, img_list=img_list, max_new_tokens=300, num_beams=1, temperature=temperature, max_length=2000)[0]
+    chatbot[-1][1] = llm_message
+    return chatbot, chat_state, img_list
+
+title = """<h1 align="center">Demo of MiniGPT-4</h1>"""
+description = """<h3>This is the demo of MiniGPT-4. Upload your images and start chatting!</h3>"""
+article = """<div style='display:flex; gap: 0.25rem; '><a href='https://minigpt-4.github.io'><img src='https://img.shields.io/badge/Project-Page-Green'></a><a href='https://github.com/Vision-CAIR/MiniGPT-4'><img src='https://img.shields.io/badge/Github-Code-blue'></a><a href='https://github.com/TsuTikgiau/blip2-llm/blob/release_prepare/MiniGPT_4.pdf'><img src='https://img.shields.io/badge/Paper-PDF-red'></a></div>
+"""
+
+#TODO show examples below
+
+with gr.Blocks() as demo:
+    gr.Markdown(title)
+    gr.Markdown(SHARED_UI_WARNING)
+    gr.Markdown(description)
+    gr.Markdown(article)
+
+    with gr.Row():
+        with gr.Column(scale=0.5):
+            image = gr.Image(type="pil")
+            upload_button = gr.Button(value="Upload & Start Chat", interactive=True, variant="primary")
+            clear = gr.Button("Restart")
+            
+            num_beams = gr.Slider(
+                minimum=1,
+                maximum=5,
+                value=1,
+                step=1,
+                interactive=True,
+                label="beam search numbers)",
+            )
+            
+            temperature = gr.Slider(
+                minimum=0.1,
+                maximum=2.0,
+                value=1.0,
+                step=0.1,
+                interactive=True,
+                label="Temperature",
+            )
+            
+
+        with gr.Column():
+            chat_state = gr.State()
+            img_list = gr.State()
+            chatbot = gr.Chatbot(label='MiniGPT-4')
+            text_input = gr.Textbox(label='User', placeholder='Please upload your image first', interactive=False)
+    
+    upload_button.click(upload_img, [image, text_input, chat_state], [image, text_input, upload_button, chat_state, img_list])
     
-    pipe = StableDiffusionPipeline.from_pretrained(os.environ['bmd'], torch_dtype=torch.float16, use_auth_token=True)
-    pipe.unet.load_attn_procs(model_path)
-    pipe.to("cuda")
-    image = pipe(prompt, num_inference_steps=num_inference_steps, guidance_scale=guidance_scale).images[0]
-    #image.save(save_name) #comment if don't want to save image
-    return image #PIL format
-
-demo = gr.Interface(fn=text_to_hair, inputs=["text", gr.Slider(5, 20, value=8, label="Guidance_scale", info="Choose between 5 and 20 to improve image's content"), 
-                                             gr.Slider(20, 500, value=20, label="Num_infer_steps", info="Choose between 20 and 500 to improve image's resolution"),
-                                            gr.Dropdown(data_into_list, interactive=True, label="Some suggestion hairstyles", info="For your suggestion and reference!")],outputs="image")
-demo.launch()
+    text_input.submit(gradio_ask, [text_input, chatbot, chat_state], [text_input, chatbot, chat_state]).then(
+        gradio_answer, [chatbot, chat_state, img_list, num_beams, temperature], [chatbot, chat_state, img_list]
+    )
+    clear.click(gradio_reset, [chat_state, img_list], [chatbot, image, text_input, upload_button, chat_state, img_list], queue=False)
+
+demo.launch(enable_queue=True)

blip2_pretrained_flant5xxl.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3839ea6c617f315ead9bf4036bbb0f0cf6bf62695ecfc14968ea626af03a29
+size 433481467

checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7b8a3c21f146654c21a1a29a577dab2c3bd1aa3b1bc902f39e86954357a811
+size 47369169

prerained_minigpt4_7b.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017a9ed588a11ed383711003cf50cf675191420a04689f682fb56fa9bbb8dcbb
+size 37907201

requirements.txt

@@ -1,6 +1,7 @@
-diffusers 
-huggingface-hub
-torch
-transformers
+--extra-index-url https://download.pytorch.org/whl/cu113
+torch==1.12.1
+torchvision==0.13.1
+salesforce-lavis
+bitsandbytes
 accelerate
-gradio==3.26.0
+git+https://github.com/huggingface/transformers.git