Update app.py

ilk deneme için.

app.py

@@ -1,43 +1,60 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from llama_cpp import Llama
 
 """
 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
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# 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
+}
 
-    messages.append({"role": "user", "content": message})
 
-    response = ""
+llama = Llama.from_pretrained(
+        repo_id="ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1-GGUF",
+        filename="*Q4_K.gguf",
+        verbose=False
+    )
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+def respond(
+    message
+):
+    # 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']}"
+    
+    # Generate the response
+    response = llama(prompt)
+    yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -46,15 +63,15 @@ 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)",
-        ),
+        #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
     ],
 )