Added the first version of model

Signed-off-by: Dipankar Das <dipankardas0115@gmail.com>

README.md

@@ -1,10 +1,12 @@
 ---
-title: Second Language Model
-emoji: 🏢
+title: ksctl GPT2 bot Model
+emoji: ☸️
 colorFrom: green
 colorTo: blue
 sdk: docker
-pinned: false
+pinned: true
 ---
 
+Used GPT2
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,12 +1,10 @@
 from fastapi import FastAPI
 from fastapi.responses import RedirectResponse
-# from transformers import pipeline
-from PIL import Image
 import requests
-from transformers import AutoProcessor, Pix2StructForConditionalGeneration
 
-processor = AutoProcessor.from_pretrained("google/pix2struct-textcaps-base")
-model = Pix2StructForConditionalGeneration.from_pretrained("google/pix2struct-textcaps-base")
+from transformers import pipeline, set_seed
+generator = pipeline('text-generation', model='gpt2')
+set_seed(42)
 
 
 app = FastAPI()
@@ -16,25 +14,6 @@ async def docs_redirect():
     return RedirectResponse(url='/docs')
 
 @app.get("/generate")
-def generate(url: str):
-    """
-    https://huggingface.co/docs/transformers/main/en/model_doc/pix2struct#transformers.Pix2StructForConditionalGeneration
-    https://huggingface.co/google/pix2struct-widget-captioning-large/blob/main/README.md
-    """
-    # url = "https://www.ilankelman.org/stopsigns/australia.jpg"
-    image = Image.open(requests.get(url, stream=True).raw)
-
-    inputs = processor(images=image, return_tensors="pt")
-
-    # autoregressive generation
-    generated_ids = model.generate(**inputs, max_new_tokens=50)
-    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    print(generated_text)
-
-    # conditional generation
-    text = "A picture of"
-    inputs = processor(text=text, images=image, return_tensors="pt", add_special_tokens=False)
-
-    generated_ids1 = model.generate(**inputs, max_new_tokens=50)
-    generated_text1 = processor.batch_decode(generated_ids1, skip_special_tokens=True)[0]
-    return {"output": {"autoregressive": generated_text, "conditional": generated_text1},}
+def generate(text: str):
+    output: list[dict] = generator(text, max_length=200, num_return_sequences=1)
+    return {"output": output}

requirements.txt

@@ -4,4 +4,3 @@ uvicorn[standard]==0.17.*
 sentencepiece==0.1.*
 torch==1.11.*
 transformers==4.*
-Pillow