Updatea app.py

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10-slim
+
+RUN useradd user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user ./ $HOME/app
+
+RUN pip install -r requirements.txt
+
+CMD fastapi run --reload --host=0.0.0.0 --port=7860

app.py

@@ -1,7 +1,74 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, Request
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+print("COSMOS Llama Chatbot is starting...")
+
+model_id = "ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1"
+
+print("Model loading started")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+print("Model loading completed")
+
+# bu mesaj değiştirilebilir ve chatbotun başlangıç mesajı olarak kullanılabilir
+initial_message = [
+    {"role": "system", "content": "Sen bir yapay zeka asistanısın. Kullanıcı sana bir görev verecek. Amacın görevi olabildiğince sadık bir şekilde tamamlamak."}
+    # Görevi yerine getirirken adım adım düşün ve adımlarını gerekçelendir.
+]
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+print("Selected device:", device)
 
 app = FastAPI()
 
-@app.get("/")
-def greet_json():
-    return {"Hello": "World!"}
+
+@app.get('/')
+def home():
+    return {"hello": "Bitfumes"}
+
+
+@app.post('/ask')
+async def ask(request: Request):
+    data = await request.json()
+    prompt = data.get("prompt")
+    if not prompt:
+        return {"error": "Prompt is missing"}
+
+    print("Device of the model:", model.device)
+    messages = initial_message.copy()
+    messages.append({"role": "user", "content": f"{prompt}"})
+
+    print("Messages:", messages)
+    print("Tokenizer process started")
+    input_ids = tokenizer.apply_chat_template(
+        messages,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    ).to(model.device)
+
+    terminators = [
+        tokenizer.eos_token_id,
+        tokenizer.convert_tokens_to_ids("<|eot_id|>")
+    ]
+    print("Tokenizer process completed")
+
+    print("Model process started")
+    outputs = model.generate(
+        input_ids,
+        max_new_tokens=256,
+        eos_token_id=terminators,
+        do_sample=True,
+        temperature=0.6,
+        top_p=0.9,
+    )
+    response = outputs[0][input_ids.shape[-1]:]
+
+    print("Tokenizer decode process started")
+    answer = tokenizer.decode(response, skip_special_tokens=True)
+
+    return {"answer": answer}

requirements.txt

@@ -1,2 +1,7 @@
-fastapi
-uvicorn[standard]
+fastapi[standard]
+uvicorn
+transformers
+torch
+accelerate>=0.26.0
+huggingface-hub
+debugpy