Upload 2 files

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+import random
+import time
+from ctransformers import AutoModelForCausalLM
+import datetime
+import os
+
+
+params = {
+        "max_new_tokens":512,
+        "stop":["<end>" ,"<|endoftext|>"],
+        "temperature":0.7,
+        "top_p":0.8,
+        "stream":True,
+        "batch_size": 8}
+
+  
+llm = AutoModelForCausalLM.from_pretrained("Aspik101/guanaco-7B-HF-pl-lora_GGML", model_type="llama")
+
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.Button("Clear")
+
+    def user(user_message, history):
+        return "", history + [[user_message, None]]
+
+    def bot(history):
+        print("Question": history)
+        stream = llm(prompt =  f"Jesteś AI assystentem. Odpowiadaj po polsku. <user>: {history}. <assistant>:", **params)
+        history[-1][1] = ""
+        answer_save = ""
+        for character in stream:
+            history[-1][1] += character
+            answer_save += character
+            time.sleep(0.005)
+            yield history
+        print("Answer": answer_save)
+        
+    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
+    clear.click(lambda: None, None, chatbot, queue=False)
+    
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+torch
+ctransformers
+gradio