Browse Source

Merge pull request #245 from Hun-Bot2/community-contributions-branch

Week1 Day 2 : Huggingface page summarization and translation
pull/253/head
Ed Donner 2 months ago committed by GitHub
parent
commit
d2027a8744
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
  1. 273
      week1/community-contributions/Week1-Day2-Ollama-Exercise.ipynb

273
week1/community-contributions/Week1-Day2-Ollama-Exercise.ipynb

@ -0,0 +1,273 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "fad31e32-2e42-42ae-ae63-c15d90292839",
"metadata": {},
"source": [
"# First Project\n",
"Ollama -> Summary\n",
"huggingface_hub -> \"facebook/m2m100_418M\" for translation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5fb79a20-a455-4d27-91a1-91958af786c1",
"metadata": {},
"outputs": [],
"source": [
"!pip install transformers datasets torch\n",
"!pip install huggingface_hub"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e95ac7f2-5192-4f83-acf3-61df30cd3109",
"metadata": {},
"outputs": [],
"source": [
"# imports\n",
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import json\n",
"import ollama"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "12276d74-0e79-4e66-9135-1c9d1a80b943",
"metadata": {},
"outputs": [],
"source": [
"class Website:\n",
" def __init__(self, url):\n",
" self.url = url\n",
" response = requests.get(url)\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
" self.title = soup.title.string if soup.title else \"No title found\"\n",
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
" irrelevant.decompose()\n",
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n",
"\n",
"huggingface_url = \"https://huggingface.co/learn/ml-for-3d-course\"\n",
"huggingface_website = Website(huggingface_url)\n",
"\n",
"huggingface_data = {\n",
" \"title\": huggingface_website.title,\n",
" \"text\": huggingface_website.text\n",
"}\n",
"print(huggingface_data)\n",
"\n",
"with open('ml_for_3d_course_data.json', 'w') as f:\n",
" json.dump(huggingface_data, f)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7d74c85c-3e09-4514-bde4-4cafc4910c52",
"metadata": {},
"outputs": [],
"source": [
"# huggingface_data 'text' value\n",
"huggingface_text = huggingface_data['text']\n",
"\n",
"# Summary\n",
"response_summary = ollama.chat(model=\"llama3.2:latest\", messages=[{\"role\": \"user\", \"content\": f\"Summarize the following text: {huggingface_text}\"}])\n",
"print(response_summary)\n",
"\n",
"# print summary\n",
"summary_huggingface_text = response_summary.message['content']\n",
"print(\"Summary Text:\", summary_huggingface_text)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d13764d5-cb76-46c5-bbe6-d132b31a9ea6",
"metadata": {},
"outputs": [],
"source": [
"# HuggingFace Translation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "08405038-4115-487f-9efc-de58572453c1",
"metadata": {},
"outputs": [],
"source": [
"class Website:\n",
" url: str\n",
" title: str\n",
" text: str\n",
"\n",
" def __init__(self, url):\n",
" self.url = url\n",
" response = requests.get(url)\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
" self.title = soup.title.string if soup.title else \"No title found\"\n",
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n",
" irrelevant.decompose()\n",
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n",
"\n",
"url = \"https://huggingface.co/learn/ml-for-3d-course\"\n",
"website = Website(url)\n",
"print(website.title) \n",
"print(website.text[:1000])\n",
"\n",
"data = {\n",
" \"title\": website.title,\n",
" \"text\": website.text\n",
"}\n",
"\n",
"with open('ml_for_3d_course_data.json', 'w') as f:\n",
" json.dump(data, f)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0632352f-4b16-4125-83bf-f3cc3aabd659",
"metadata": {},
"outputs": [],
"source": [
"print(data)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a85f8625-725d-4d7f-8cb7-8da4276f81cf",
"metadata": {},
"outputs": [],
"source": [
"!pip install sacremoses"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c800cea4-f4a4-4e41-9637-31ff11afb256",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer\n",
"\n",
"# Load the M2M100 model and tokenizer\n",
"model_name = \"facebook/m2m100_418M\"\n",
"model = M2M100ForConditionalGeneration.from_pretrained(model_name)\n",
"tokenizer = M2M100Tokenizer.from_pretrained(model_name)\n",
"\n",
"# Load the saved JSON file\n",
"with open('ml_for_3d_course_data.json', 'r') as f:\n",
" data = json.load(f)\n",
"\n",
"# Extract text from the loaded data\n",
"text = data[\"text\"]\n",
"\n",
"# Set the source language to English and target language to Korean\n",
"source_lang = \"en\"\n",
"target_lang = \"ko\"\n",
"\n",
"# Set the language for tokenizer (important for M2M100)\n",
"tokenizer.src_lang = source_lang\n",
"tokenizer.tgt_lang = target_lang\n",
"\n",
"# Split text into smaller chunks if it's too large\n",
"# This step ensures we don't exceed the model's maximum length (512 tokens)\n",
"max_input_length = 512\n",
"chunks = [text[i:i+max_input_length] for i in range(0, len(text), max_input_length)]\n",
"\n",
"print(chunks)\n",
"# Initialize a list to hold the translated text\n",
"translated_chunks = []\n",
"\n",
"# Iterate through each chunk and translate it\n",
"for chunk in chunks:\n",
" # Tokenize the chunk\n",
" encoded = tokenizer(chunk, return_tensors=\"pt\", padding=True, truncation=True, max_length=512)\n",
"\n",
" # Generate translation from the model, forcing the output to be in Korean\n",
" generated_tokens = model.generate(**encoded, forced_bos_token_id=tokenizer.get_lang_id(target_lang), max_length=512)\n",
"\n",
" # Decode the translated tokens to text\n",
" translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]\n",
" translated_chunks.append(translated_text)\n",
"\n",
"# Combine all translated chunks back together\n",
"final_translated_text = ' '.join(translated_chunks)\n",
"print(\"Translated Text:\", final_translated_text)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ffe0f264-a588-422f-a6e1-b60504d1e02c",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import requests\n",
"\n",
"# Ollama API URL 설정\n",
"ollama_url = \"http://localhost:11411/v1/models/facebook/m2m100_418M/generate\"\n",
"\n",
"# 저장된 JSON 파일 로드\n",
"with open('ml_for_3d_course_data.json', 'r') as f:\n",
" data = json.load(f)\n",
"\n",
"# 텍스트 추출\n",
"course_text = data[\"text\"]\n",
"\n",
"# 번역할 소스 언어 및 타겟 언어 설정\n",
"source_language = \"en\"\n",
"target_language = \"ko\"\n",
"\n",
"# 데이터 준비\n",
"payload = {\n",
" \"input_text\": course_text,\n",
" \"src_lang\": source_language,\n",
" \"tgt_lang\": target_language\n",
"}\n",
"\n",
"# API 호출\n",
"response = requests.post(ollama_url, json=payload)\n",
"\n",
"# 응답 확인\n",
"if response.status_code == 200:\n",
" translated_course_text = response.json().get(\"translated_text\", \"Translation failed\")\n",
" print(\"Translated Course Text:\", translated_course_text)\n",
"else:\n",
" print(f\"Error {response.status_code}: {response.text}\")\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading…
Cancel
Save