{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\ZZ029K826\\Documents\\GitHub\\llm-bill-chat-app\\.venv\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", " from .autonotebook import tqdm as notebook_tqdm\n" ] } ], "source": [ "from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "model_name = \"ai-forever/mGPT-1.3B-romanian\"\n", "tokenizer = AutoTokenizer.from_pretrained(model_name)\n", "model = AutoModelForCausalLM.from_pretrained(model_name)\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Device set to use cpu\n" ] } ], "source": [ "chat_model = pipeline(\n", " \"text-generation\",\n", " model=model,\n", " tokenizer=tokenizer,\n", " device=-1, # Use CPU\n", " max_length=300,\n", " max_new_tokens=100,\n", " truncation=True\n", ")\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "c:\\Users\\ZZ029K826\\Documents\\GitHub\\llm-bill-chat-app\\.venv\\Lib\\site-packages\\transformers\\generation\\configuration_utils.py:628: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.7` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.\n", " warnings.warn(\n", "c:\\Users\\ZZ029K826\\Documents\\GitHub\\llm-bill-chat-app\\.venv\\Lib\\site-packages\\transformers\\generation\\configuration_utils.py:633: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n", " warnings.warn(\n", "Both `max_new_tokens` (=100) and `max_length`(=300) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Cum te simți astăzi?\n", "\n", "- Nu mă mai gândesc la asta. - Ba da, sunt bine!\n", "\n", "Nu e nimic de făcut în legatura cu tata... dar nu vreau ca el sa se raneasca pe mine acolo unde este locul meu preferat: un apartament mare si frumoasa casa din New York City care are o proprietate privată pentru copiii lui Michael Jackson şi familia ei.\n", "\n", "\n" ] } ], "source": [ "def generate_response(user_input, temperature=0.7, top_k=50, top_p=0.9, repetition_penalty=1.2):\n", " response = chat_model(\n", " user_input,\n", " max_new_tokens=100,\n", " temperature=temperature,\n", " top_k=top_k,\n", " top_p=top_p,\n", " repetition_penalty=repetition_penalty\n", " )\n", " return response[0]['generated_text']\n", "\n", "# Test the function with adjusted parameters\n", "user_input = \"Cum te simți astăzi?\"\n", "response = generate_response(user_input)\n", "print(response)" ] } ], "metadata": { "kernelspec": { "display_name": ".venv", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.5" } }, "nbformat": 4, "nbformat_minor": 2 }