Skip to content

Instantly share code, notes, and snippets.

View schroneko's full-sized avatar

ぬこぬこ | NUKO schroneko

View GitHub Profile
export const hello = () => {
console.log('hello')
}
@schroneko
schroneko / main.py
Created January 4, 2024 02:34
test: oshizo/japanese-sexual-moderation-v2
## https://huggingface.co/oshizo/japanese-sexual-moderation-v2
## How to use
## $ python3 -m venv venv && source venv/bin/activate
## $ pip install transformers torch sentencepiece
## $ python main.py --input "富士山は日本で一番高い山です。"
import torch
import argparse
from transformers import AutoModelForSequenceClassification, AutoTokenizer

Anthropic Cookbook ひとことまとめ

The Bible

https://github.com/anthropics/anthropic-cookbook

misc

read_web_pages_with_haiku.ipynb: PythonでAnthropicのClaude APIを使用してWebページのコンテンツを要約する方法を説明しています。

@schroneko
schroneko / ic-light-colab-zho-jp.ipynb
Created May 9, 2024 05:53
IC-Light Colab【-Zho-制作】jp
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@schroneko
schroneko / aivis-cli.zsh
Created December 8, 2024 09:12
aivis-cli.zsh
#!/usr/bin/env zsh
# Default settings
HOST="127.0.0.1"
PORT="10101"
SPEAKER="888753760" # Default speaker ID (Anneli - ノーマル)
TEXT=""
# Get the script name without any prefix
SCRIPT_NAME=$(basename "$0")
from typing_extensions import TypedDict, Literal
import random
from langgraph.graph import StateGraph, START
from langgraph.types import Command
# Define graph state
class State(TypedDict):
foo: str
# Define the nodes
import contextlib
import wave
import logging
import asyncio
import os
import sounddevice as sd
import soundfile as sf
from google import genai
# ロガーの設定
import re
from bs4 import BeautifulSoup
import json
def extract_rss_urls(html_file):
with open(html_file, 'r', encoding='utf-8') as f:
html_content = f.read()
soup = BeautifulSoup(html_content, 'html.parser')
import email
import os
from email import policy
from email.parser import BytesParser
def extract_email_content(eml_file):
"""Extract plain text content from email file."""
with open(eml_file, 'rb') as f:
msg = BytesParser(policy=policy.default).parse(f)
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import datasets, transforms
class ConvNet(nn.Module):
def __init__(self):
super(ConvNet, self).__init__()
# 畳み込み層
self.conv1 = nn.Conv2d(1, 32, 3, padding=1)