Upload 5 files

.dockerignore

@@ -0,0 +1,5 @@
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+venv/

Dockerfile

@@ -0,0 +1,17 @@
+# Gunakan image Python yang ringan
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Salin dependensi
+COPY requirements.txt .
+
+# Install dependensi
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Salin kode aplikasi
+COPY . .
+
+# Jalankan FastAPI
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,11 +1,3 @@
----
-title: Example LLM Description
-emoji: ⚡
-colorFrom: gray
-colorTo: pink
-sdk: docker
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Hello World
+
+This is a simple repository to get started with GitHub.

app.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+app = FastAPI()
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("unsloth/Llama-3.2-1B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-1B-Instruct").to("cpu")  # Gunakan CPU karena HF Spaces gratis hanya menyediakan CPU
+
+@app.get("/")
+def home():
+    return {"message": "FastAPI running with Llama-3.2-1B-Instruct"}
+
+@app.post("/generate")
+def generate_text(prompt: str):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cpu")  # Gunakan CPU
+    output = model.generate(**inputs, max_length=200)
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    return {"generated_text": generated_text}

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+transformers
+torch
+unsloth