Create requirements.txt

Update Dockerfile

Update main.py

Update Dockerfile

Update main.py

Update main.py

Update README.md

model added

Update Dockerfile

Update Dockerfile

Update requirements.txt

Update main.py

Update Dockerfile

Update main.py

Update main.py

Update main.py

Update main.py

Update main.py

Update main.py

Update main.py

Update main.py

Dockerfile

@@ -1,14 +1,27 @@
+# Use the official Python 3.9 image
 FROM python:3.9
 
+# Set the working directory to /code
 WORKDIR /code
 
+# Copy the current directory contents into the container at /code
 COPY ./requirements.txt /code/requirements.txt
 
+# Install requirements.txt
 RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
-COPY  ./__init__.py /code/__init__.py
-COPY ./credentials.env /code/credentials.env
-COPY ./rag_retriver.py /code/rag_retriver.py
-COPY ./main.py /code/main.py
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
 
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,10 @@
 ---
 title: UvicornGpt2
-emoji: 📉
-colorFrom: indigo
-colorTo: yellow
+emoji: 😻
+colorFrom: purple
+colorTo: pink
 sdk: docker
 pinned: false
+license: mit
 ---
-
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -1,36 +1,56 @@
+# from fastapi.staticfiles import StaticFiles
+# from fastapi.responses import FileResponse
 from fastapi import FastAPI
 from pydantic import BaseModel
-from transformers import GPT2Tokenizer, GPT2Model
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
 from langchain.prompts import PromptTemplate
 
 app = FastAPI()
 
 tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
-model = GPT2Model.from_pretrained('gpt2')
+model = GPT2LMHeadModel.from_pretrained('gpt2')
 
 
 class TextRequest(BaseModel):
-    text: str
+    question: str
 
 
-def preprocess_text(text: str):
-    return text.lower()
+def preprocess_text(question: str):
+    return question.lower()
 
 
 def classify_text(question: str):
-    prompt_template = PromptTemplate(template="Answer the following question and classify it: {question}", input_variables = ["question"], output_variables=["answer", "classification"])
-    # Model loading
-    format_prompt = prompt_template.format(question=question)
+    prompt_template = PromptTemplate(template="Answer the following question and classify it: {question}",
+                                     input_variables=["question"])
+    format_prompt = prompt_template.format(question=input_text)
     encoded_input = tokenizer(format_prompt, return_tensors='pt')
-    output = model(encoded_input)
-    # chain = LLMChain(llm=llm, prompt=prompt_template, verbose=True)
-    # response = chain({"question": question})
-    return output
+    # Run the model
+    output = model.generate(**encoded_input)  # Use generate method for text generation
+    # Decode the model output to text
+    decoded_output = tokenizer.decode(output[0])
+    response_text = decoded_output.split('\n\n')
+    answer=response_text[1]
+    return {"answer": answer}
 
 
 @app.post("/classify")
 async def classify_text_endpoint(request: TextRequest):
-    preprocessed_text = preprocess_text(request.text)
+    preprocessed_text = preprocess_text(request.question)
     response = classify_text(preprocessed_text)
-    answer = response['text']
-    return {"answer": answer}
+    return response
+
+
+# 
+# 
+# @app.get("/infer_t5")
+# def t5(input):
+#     preprocessed_text = preprocess_text(request.text)
+#     response = classify_text(preprocessed_text)
+#     output = pipe_flan(input)
+#     return {"output": output[0]["generated_text"]}
+# 
+# app.mount("/", StaticFiles(directory="static", html=True), name="static")
+# 
+# @app.get("/")
+# def index() -> FileResponse:
+#   return FileResponse(path="/app/static/index.html", media_type="text/html")

models--gpt2/refs/main

@@ -0,0 +1 @@
+607a30d783dfa663caf39e06633721c8d4cfcd7e

models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "vocab_size": 50257
+}

models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248dfc3911869ec493c76e65bf2fcf7f615828b0254c12b473182f0f81d3a707
+size 548105171

models--gpt2/snapshots/607a30d783dfa663caf39e06633721c8d4cfcd7e/tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

requirements.txt

@@ -0,0 +1,9 @@
+langchain==0.2.5
+langchain-community==0.2.5
+python-multipart==0.0.9
+fastapi==0.111.0
+pydantic==2.7.3
+uvicorn==0.30.1
+requests==2.32.3
+transformers==4.41.2
+torch==2.3.1