Skip to content

Instantly share code, notes, and snippets.

@xiaolai
xiaolai / iina-as-an-audiobook-player.md
Last active June 25, 2023 23:44
A better way to listen audiobook on MacOS
@sunlei
sunlei / translate-srt.py
Last active January 23, 2024 14:52
使用 ChatGPT Few-shot 翻译 SRT 字幕
import json
import os
import requests
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
OPENAI_BASE_URL = "https://api.openai.com/v1/chat/completions"
def translator(srt):
@benjaminshafii
benjaminshafii / basel.js
Created August 10, 2023 00:40
Auto-generate OpenAPI spec w/ Anthropic Claude from any programming language
const Anthropic = require('@anthropic-ai/sdk');
const path = require('path');
const YAML = require('yaml');
const fs = require('fs');
// Initialize Anthropic SDK
const anthropic = new Anthropic({
apiKey: process.env.ANTHROPIC_API_KEY,
});
@veekaybee
veekaybee / normcore-llm.md
Last active October 22, 2025 08:37
Normcore LLM Reads

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Screenshot 2023-12-18 at 10 40 27 PM

Pre-Transformer Models

@JimLiu
JimLiu / ChatGPT-Translate-Long-Text.js
Last active April 8, 2024 07:26
使用ChatGPT自动分页翻译长文
// WARNING:此脚本仅做学习和演示用途,在不了解其用途前不建议使用
// 本脚本的用途是将输入内容分页,每次提取一页内容,编辑第二条消息,发送,然后收集结果
// 使用前,需要有两条消息,参考模板 https://chat.openai.com/share/17195108-30c2-4c62-8d59-980ca645f111
// 演示视频: https://www.bilibili.com/video/BV1tp4y1c7ME/?vd_source=e71f65cbc40a72fce570b20ffcb28b22
//
(function (fullText) {
const wait = (ms) => new Promise((resolve) => setTimeout(resolve, ms));
const groupSentences = (fullText, maxCharecters = 2800) => {
const sentences = fullText.split("\n").filter((line) => line.trim().length > 0);
@mberman84
mberman84 / main.py
Created November 10, 2023 16:17
OpenChat Code
import requests
import json
import gradio as gr
url = "http://localhost:11434/api/generate"
headers = {
'Content-Type': 'application/json',
}
@etrobot
etrobot / oneclicknewsvideo.ipynb
Created November 19, 2023 09:08
OneClickNewsVideo.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@ivanfioravanti
ivanfioravanti / gist:bcacc48ef68b02e9b7a4034161824287
Created January 25, 2024 00:01
Fine tuning dataset generation wiht Ollama python library
import json
import os
import ollama
def query_ollama(prompt, model='openhermes:7b-mistral-v2.5-q6_K', context=''):
response = ollama.generate(
model=model,
prompt=context + prompt)
return response['response'].strip()
@alexweberk
alexweberk / mlx_finetuning_gemma.ipynb
Last active October 27, 2025 21:47
MLX Fine-tuning Google Gemma
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@unixzii
unixzii / ForceEnablingXcodeLLM.md
Last active September 12, 2025 08:05
A guide to force enabling Xcode LLM feature on China-SKU Macs.

Introduction

Apple restricted the access to Xcode LLM (Predictive code completion) feature on China models of Mac. This guide provides a way to bypass that restriction. It's verified on macOS 15.0 Beta (24A5264n), but there is no guarentee that it will always work on later macOS versions.

Prerequisites

  • Xcode is installed and run at least once.
  • SIP debugging restrictions are disabled (via csrutil enable --without debug command in recovery mode).

Disclaimer