Subiendo archivos de la API a Hugging Face

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.9
+
+WORKDIR /app
+COPY . /app
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 7860
+
+CMD ["uvicorn", "api:app", "--host", "0.0.0.0", "--port", "7860"]

api.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Inicializar FastAPI
+app = FastAPI()
+
+# Cargar modelo y tokenizer
+MODEL_PATH = "models/phi2_finetuned_full"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = AutoModelForCausalLM.from_pretrained(MODEL_PATH, torch_dtype=torch.float16, device_map="cpu")
+
+@app.get("/")
+def home():
+    return {"message": "API de Chatbot con Phi-2 está en funcionamiento"}
+
+@app.post("/predict/")
+def predict(input_text: str):
+    """Genera una respuesta basada en el input del usuario."""
+    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_length=150)
+    response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": response_text}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+torch
+transformers
+fastapi
+uvicorn
+torch
+transformers