[Python] How do I load huggingface model locally to use with langchain and host and streamlit?

I am trying to make an AI app with langchain and Huggingface. I got the following error:

{ "error": "Could not load model paragon-AI/blip2-image-to-text with any of the following classes: (<class 'transformers.models.blip_2.modeling_blip_2.Blip2ForConditionalGeneration'>,). See the original errors:\n\nwhile loading with Blip2ForConditionalGeneration, an error is thrown:\nTraceback (most recent call last):\n File "/src/transformers/src/transformers/pipelines/base.py", line 269, in infer_framework_load_model\n model = model_class.from_pretrained(model, **kwargs)\n File "/src/transformers/src/transformers/modeling_utils.py", line 3138, in from_pretrained\n raise EnvironmentError(\nOSError: paragon-AI/blip2-image-to-text does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.\n\n\n" }
​

import streamlit as st
import requests
from PIL import Image
from io import BytesIO
from transformers import AutoModelForCausalLM

def main():
st.title("Image to Text and Audio Converter")

# Upload image file
uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
# Display uploaded image
st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)

# Convert image to text
st.subheader("Image to Text")
text_output = convert_image_to_text(uploaded_file)
st.write(text_output)

# Convert image to audio
st.subheader("Image to Audio")
audio_output = convert_image_to_audio(uploaded_file)
st.audio(audio_output)

def convert_image_to_text(image_file):
IMAGE_TO_TEXT_API_URL = "https://api-inference.huggingface.co/models/paragon-AI/blip2-image-to-text"
IMAGE_TO_TEXT_HEADERS = {"Authorization": "Bearer apikey"}

response = requests.post(IMAGE_TO_TEXT_API_URL, headers=IMAGE_TO_TEXT_HEADERS, files={"file": image_file})
return response.json()

def convert_image_to_audio(image_file):
IMAGE_TO_AUDIO_API_URL = "https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-large"
IMAGE_TO_AUDIO_HEADERS = {"Authorization": "Bearer apikey"}

response = requests.post(IMAGE_TO_AUDIO_API_URL, headers=IMAGE_TO_AUDIO_HEADERS, files={"file": image_file})
return response.content

if __name__ == "__main__":
main()

Continue reading...