Update app.py

fine tuned halini gpu'ya kurdum.quantized çalışmadı ama cpu'da çalıştığından çökmüş de olabilir bakılacak.

app.py

@@ -1,6 +1,19 @@
 import gradio as gr
+import spaces
 from huggingface_hub import InferenceClient
-from llama_cpp import Llama
+#from llama_cpp import Llama
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -8,55 +21,53 @@ For more information on `huggingface_hub` Inference API support, please check th
 # client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
-# Define the inference parameters
-inference_params = {
-    "n_threads": 4,
-    "n_predict": -1,
-    "top_k": 40,
-    "min_p": 0.05,
-    "top_p": 0.95,
-    "temp": 0.8,
-    "repeat_penalty": 1.1,
-    "input_prefix": "<|start_header_id|>user<|end_header_id|>\\n\\n",
-    "input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n",
-    "antiprompt": [],
-    "pre_prompt": "Sen bir yapay zeka asistanısın. Kullanıcı sana bir görev verecek. Amacın görevi olabildiğince sadık bir şekilde tamamlamak.",
-    "pre_prompt_suffix": "<|eot_id|>",
-    "pre_prompt_prefix": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\\n\\n",
-    "seed": -1,
-    "tfs_z": 1,
-    "typical_p": 1,
-    "repeat_last_n": 64,
-    "frequency_penalty": 0,
-    "presence_penalty": 0,
-    "n_keep": 0,
-    "logit_bias": {},
-    "mirostat": 0,
-    "mirostat_tau": 5,
-    "mirostat_eta": 0.1,
-    "memory_f16": True,
-    "multiline_input": False,
-    "penalize_nl": True
-}
-
-
-llama = Llama.from_pretrained(
-        repo_id="ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1-GGUF",
-        filename="*Q4_K.gguf",
-        verbose=False
-    )
-
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
+    max_tokens,
+    temperature,
+    top_p,
 ):
-    # Construct the prompt
-    prompt = f"{inference_params['pre_prompt_prefix']}{inference_params['pre_prompt']}\n\n{inference_params['input_prefix']}{message}{inference_params['input_suffix']}"
+
+    print("response girildi")
+
+    messages = [
+    {"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."},
+    {"role": "user", "content": message},
+    ]
+
     
-    # Generate the response
-    response = llama(prompt)
-    yield response
+    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("cevaba girildi")
+
+    
+
+    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("cevap döndü")
+    
+    
+    yield tokenizer.decode(response, skip_special_tokens=True)
+
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -64,16 +75,16 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message")#,
-        #gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        #gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        #gr.Slider(
-        #    minimum=0.1,
-        #    maximum=1.0,
-        #    value=0.95,
-        #    step=0.05,
-        #    label="Top-p (nucleus sampling)",
-        #), # inference parametreleri eklenecek
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+           minimum=0.1,
+           maximum=1.0,
+           value=0.95,
+           step=0.05,
+           label="Top-p (nucleus sampling)",
+        ), # inference parametreleri eklenecek
     ],
 )