feat: gradio for flamingo-models[QA+COT]

app.py

@@ -0,0 +1,79 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import matplotlib.pyplot as plt
+import torch
+from flamingo_mini_task.utils import load_url
+from flamingo_mini_task import FlamingoModel, FlamingoProcessor
+from datasets import load_dataset,concatenate_datasets
+from PIL import Image
+
+
+flamingo_megatiny_captioning_models = {
+    'flamingo-tiny-scienceQA[COT+QA]': {
+        'model': FlamingoModel.from_pretrained('TheMrguiller/Flamingo-tiny_ScienceQA_COT-QA'),
+    },
+    'flamingo-mini-bilbaocaptions-scienceQA[QA]': {
+        'model': FlamingoModel.from_pretrained('TheMrguiller/Flamingo-mini-Bilbao_Captions-task_BilbaoQA-ScienceQA'),
+    },
+    'flamingo-megatiny-opt-scienceQA[QA]':{
+        'model': FlamingoModel.from_pretrained('landersanmi/flamingo-megatiny-opt-QA')
+    },
+}
+
+
+def generate_text(image, question, option_a, option_b, option_c, option_d, cot_checkbox, model_name):
+    model = flamingo_megatiny_captioning_models[model_name]['model']
+    processor = FlamingoProcessor(model.config)
+
+    prompt = ""
+    if cot_checkbox:
+        prompt += "[COT]"
+    else:
+        prompt += "[QA]"
+    
+    prompt += "[CONTEXT]<image>[QUESTION]{} [OPTIONS] (A) {} (B) {} (C) {} (D) {} [ANSWER]".format(question,
+                                                                                                   option_a,
+                                                                                                   option_b,
+                                                                                                   option_c,
+                                                                                                   option_d)
+
+    print(prompt)
+    prediction = model.generate_captions(images = image,
+                                         processor = processor,
+                                         prompt = prompt,
+                                        )
+
+    return prediction[0]
+
+
+
+
+image_input = gr.Image(value="giraffes.jpg")
+question_input = gr.inputs.Textbox(default="Which animal is this?")
+opt_a_input = gr.inputs.Textbox(default="Dog")
+opt_b_input = gr.inputs.Textbox(default="Cat")
+opt_c_input = gr.inputs.Textbox(default="Giraffe")
+opt_d_input = gr.inputs.Textbox(default="Horse")
+cot_checkbox = gr.inputs.Checkbox(label="Generate COT")
+select_model = gr.inputs.Dropdown(choices=list(flamingo_megatiny_captioning_models.keys()))
+
+text_output = gr.outputs.Textbox()
+
+# Create the Gradio interface
+gr.Interface(
+    fn=generate_text,
+    inputs=[image_input, 
+            question_input, 
+            opt_a_input, 
+            opt_b_input, 
+            opt_c_input, 
+            opt_d_input, 
+            cot_checkbox,
+            select_model
+           ],
+    outputs=text_output,
+    title='Generate answers from MCQ',
+    description='Generate answers from Multiple Choice Questions or generate a Chain Of Though about the question and the options given',
+    theme='default'
+).launch()

requirements.txt

@@ -0,0 +1,120 @@
+absl-py==1.4.0
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==5.0.1
+anyio==3.7.0
+appdirs==1.4.4
+asttokens==2.2.1
+async-timeout==4.0.2
+attrs==23.1.0
+backcall==0.2.0
+beautifulsoup4==4.12.2
+brotlipy==0.7.0
+charset-normalizer==2.1.1
+click==7.1.2
+comm==0.1.3
+contourpy==1.0.7
+cycler==0.11.0
+debugpy==1.6.7
+decorator==5.1.1
+deep-translator==1.11.0
+dill==0.3.6
+docker-pycreds==0.4.0
+einops==0.6.1
+einops-exts==0.0.4
+evaluate==0.4.0
+exceptiongroup==1.1.1
+executing==1.2.0
+fastapi==0.95.2
+ffmpy==0.3.0
+git+https://github.com/TheMrguiller/MUCSI_Modal.git@main#subdirectory=flamingo-train_task
+fonttools==4.39.3
+frozenlist==1.3.3
+fsspec==2023.5.0
+gitdb==4.0.10
+GitPython==3.1.31
+gradio==3.33.1
+gradio_client==0.2.5
+h11==0.14.0
+httpcore==0.17.2
+httpx==0.24.1
+huggingface-hub==0.14.1
+install==1.3.5
+ipykernel==6.23.1
+ipython==8.13.2
+jedi==0.18.2
+joblib==1.2.0
+jsonschema==4.17.3
+jupyter_client==8.2.0
+jupyter_core==5.3.0
+kiwisolver==1.4.4
+langdetect==1.0.9
+linkify-it-py==2.0.2
+markdown-it-py==2.2.0
+matplotlib==3.7.1
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+mpmath==1.2.1
+multidict==6.0.4
+multiprocess==0.70.14
+nest-asyncio==1.5.6
+nltk==3.8
+orjson==3.9.0
+packaging==23.1
+pandas==2.0.1
+parso==0.8.3
+pathtools==0.1.2
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.4.0
+platformdirs==3.5.1
+prompt-toolkit==3.0.38
+protobuf==4.23.0
+psutil==5.9.5
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==12.0.0
+pycocotools==2.0.6
+pydantic==1.10.8
+pydub==0.25.1
+Pygments==2.15.1
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0
+pyzmq==25.0.2
+regex==2023.5.5
+responses==0.18.0
+rfc3987==1.3.8
+rouge-score==0.1.2
+semantic-version==2.10.0
+sentry-sdk==1.22.2
+setproctitle==1.3.2
+six==1.16.0
+smmap==5.0.0
+sniffio==1.3.0
+soupsieve==2.4.1
+stack-data==0.6.2
+starlette==0.27.0
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.1
+torchaudio==2.0.2
+torchvision==0.15.2
+tornado==6.3.2
+tqdm==4.65.0
+traitlets==5.9.0
+transformers==4.28.1
+triton==2.0.0
+tzdata==2023.3
+uc-micro-py==1.0.2
+uvicorn==0.22.0
+wandb==0.15.2
+wcwidth==0.2.6
+websockets==11.0.3
+xxhash==3.2.0
+yarl==1.9.2