Upload 4 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,25 +1,36 @@
-import os
-import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# Hàm để sử dụng mô hình trả lời câu hỏi
-def chatbot(input_text):
-    # Đảm bảo bạn đã load mô hình và tokenizer
-    model_name = "Viet-Mistral/Vistral-7B-Chat"  # Hoặc tên mô hình bạn đang sử dụng
-    hf_token = os.getenv("HF_AUTH_TOKEN")
-    model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)
-    tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
-    
-    # Xử lý đầu vào và tạo ra câu trả lời
-    inputs = tokenizer(input_text, return_tensors="pt")
-    outputs = model.generate(inputs["input_ids"])
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    # Trả về câu trả lời
-    return response
-
-# Tạo giao diện Gradio
-iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", live=True)
-
-# Khởi động giao diện
-iface.launch()
+import os
+import subprocess
+import gradio as gr
+from llama_cpp import Llama
+
+MODEL_URL = "https://drive.google.com/uc?id=1aYzH-tUYl8LT-0KdO1NK9mA1w37CkM7s&export=download"
+MODEL_PATH = "model/phogpt-4b-chat-q4_K_M.gguf"
+
+# Tải model nếu chưa có
+def download_model():
+    if not os.path.exists(MODEL_PATH):
+        os.makedirs("model", exist_ok=True)
+        print("⬇️ Tải model từ Google Drive...")
+        subprocess.run([
+            "wget", "-O", MODEL_PATH, MODEL_URL
+        ])
+        print("✅ Tải xong!")
+
+download_model()
+
+# Load model
+llm = Llama(
+    model_path=MODEL_PATH,
+    n_ctx=2048,
+    n_threads=4,
+    n_gpu_layers=35,
+    verbose=True
+)
+
+def chat_fn(message, history):
+    prompt = f"<|user|>\n{message}\n<|assistant|>\n"
+    response = llm(prompt, max_tokens=512, stop=["<|user|>"], echo=False)
+    output = response["choices"][0]["text"].strip()
+    return output
+
+gr.ChatInterface(chat_fn, title="🧠 PhoGPT-4B Chatbot (Tiếng Việt)").launch()

requirements.txt

@@ -1,4 +1,2 @@
-torch
-transformers
-gradio
-accelerate
+gradio
+llama-cpp-python>=0.2.38