first commit

Dockerfile

@@ -0,0 +1,33 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the requirements file
+COPY requirements.txt .
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --upgrade pip
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+RUN pip install --no-cache-dir torch transformers
+
+# Install supervisor to manage multiple processes
+RUN apt-get update && apt-get install -y supervisor \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Copy the application code
+COPY . .
+
+# Expose the necessary ports
+EXPOSE 8501 8502
+
+# Create a supervisor configuration file
+RUN mkdir -p /etc/supervisor/conf.d/
+
+COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# Command to start supervisor
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

app.py

@@ -0,0 +1,25 @@
+from fastapi import FastAPI, File, UploadFile
+from PIL import Image
+from transformers import AutoProcessor, Blip2ForConditionalGeneration
+import torch
+import io
+
+app = FastAPI()
+
+# Load the model and processor
+model = Blip2ForConditionalGeneration.from_pretrained("ybelkada/blip2-opt-2.7b-fp16-sharded")
+model.load_adapter('blip-cpu-model')
+processor = AutoProcessor.from_pretrained("Salesforce/blip2-opt-2.7b")
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+@app.post("/generate-caption/")
+async def generate_caption(file: UploadFile = File(...)):
+    image = Image.open(io.BytesIO(await file.read()))
+    inputs = processor(images=image, return_tensors="pt").to(device, torch.float16)
+    
+    with torch.no_grad():
+        caption_ids = model.generate(**inputs, max_length=128)
+        caption = processor.decode(caption_ids[0], skip_special_tokens=True)
+    
+    return {"caption": caption}

blip-cpu-model/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Blip2ForConditionalGeneration",
+    "parent_library": "transformers.models.blip_2.modeling_blip_2"
+  },
+  "base_model_name_or_path": "ybelkada/blip2-opt-2.7b-fp16-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

blip-cpu-model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1fd9f411ea444e61454170a435b016b5e69a23fd7a985c1c6f860ed55b16b63
+size 83906272

blip-cpu-model/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "ybelkada/blip2-opt-2.7b-fp16-sharded",
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "classifier_dropout": null,
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "_name_or_path": "facebook/opt-2.7b",
+    "activation_dropout": 0.0,
+    "architectures": [
+      "OPTForCausalLM"
+    ],
+    "eos_token_id": 50118,
+    "ffn_dim": 10240,
+    "hidden_size": 2560,
+    "model_type": "opt",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "prefix": "</s>",
+    "torch_dtype": "float16",
+    "word_embed_proj_dim": 2560
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "layer_norm_eps": 1e-05,
+    "model_type": "blip_2_vision_model",
+    "num_channels": 3,
+    "projection_dim": 512
+  }
+}

blip-cpu-model/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 50118,
+  "pad_token_id": 1,
+  "transformers_version": "4.37.2"
+}

blip-saved-model/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ybelkada/blip2-opt-2.7b-fp16-sharded
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.1.dev0

blip-saved-model/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Blip2ForConditionalGeneration",
+    "parent_library": "transformers.models.blip_2.modeling_blip_2"
+  },
+  "base_model_name_or_path": "ybelkada/blip2-opt-2.7b-fp16-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

blip-saved-model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1fd9f411ea444e61454170a435b016b5e69a23fd7a985c1c6f860ed55b16b63
+size 83906272

docker-compose.yml

@@ -0,0 +1,20 @@
+version: '3.8'
+
+services:
+  fastapi:
+    build:
+      context: .
+      dockerfile: Dockerfile.fastapi
+    ports:
+      - "8000:8000"
+    restart: always
+
+  streamlit:
+    build:
+      context: .
+      dockerfile: Dockerfile.streamlit
+    ports:
+      - "8501:8501"
+    restart: always
+    depends_on:
+      - fastapi

requirements.txt

@@ -0,0 +1,11 @@
+fastapi==0.111.0
+pillow==10.3.0
+pydantic==1.10.16
+streamlit==1.37.1
+supervisor
+uvicorn==0.30.1
+typing_extensions
+accelerate
+huggingface_hub
+bitsandbytes
+peft

streamlit_app.py

@@ -0,0 +1,18 @@
+import streamlit as st
+import requests
+from PIL import Image
+
+st.title("Image Captioning with Fine-Tuned BLiPv2 Model")
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+    
+    files = {"file": uploaded_file.getvalue()}
+    response = requests.post("http://localhost:8501/generate-caption/", files=files)
+    caption = response.json().get("caption")
+    
+    st.write("Generated Caption:")
+    st.write(f"**{caption}**")

supervisord.conf

@@ -0,0 +1,19 @@
+[supervisord]
+nodaemon=true
+user=root
+
+[program:fastapi]
+command=uvicorn app:app --host 0.0.0.0 --port 8501
+directory=/app
+autostart=true
+autorestart=true
+stderr_logfile=/var/log/fastapi.err.log
+stdout_logfile=/var/log/fastapi.out.log
+
+[program:streamlit]
+command=streamlit run streamlit_app.py --server.port=8502 --server.address=0.0.0.0
+directory=/app
+autostart=true
+autorestart=true
+stderr_logfile=/var/log/streamlit.err.log
+stdout_logfile=/var/log/streamlit.out.log