Use this skill to fetch the transcript of a YouTube video, with or without timestamps.
Use this skill with Claude (by extracting it to .claude/skills/) or with any other agent using Skillz.
Note: This skill is unlikely to run successfully on the Claude web app, since access to YouTube is blocked. Use it with Claude Code or other local agents.
| # train_grpo.py | |
| # | |
| # See https://github.com/willccbb/verifiers for ongoing developments | |
| # | |
| """ | |
| citation: | |
| @misc{brown2025grpodemo, | |
| title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models}, | |
| author={Brown, William}, |
| ministrations | |
| audible pop | |
| rivulets of | |
| admit it | |
| the ball is in your court | |
| the game is on | |
| the choice is yours | |
| I don't bite... unless you want me to | |
| half-lidded eyes | |
| she worries her bottom lip |
| """ | |
| a simple script that reads tweets inside a json file, uses openai to compute embeddings and creates two files, metadata.tsv and output.tsv, which cam be used to visualise the tweets and their embeddings in TensorFlow Projector (https://projector.tensorflow.org/) | |
| """ | |
| # obtain tweets.json from https://gist.github.com/gd3kr/948296cf675469f5028911f8eb276dbc | |
| import pandas as pd | |
| import json | |
| from openai import OpenAI |
| import os | |
| import gradio as gr | |
| import torch | |
| from infer import get_net_g, infer | |
| import utils | |
| voice_keys = ["dec", "flow"] | |
| speech_style_keys = ["enc_p"] |
| """ | |
| The code below combines approaches published by both @eugene-yh and @jinyongyoo on Github. | |
| Thanks for the contributions guys! | |
| """ | |
| import torch | |
| import peft |
| from datasets import load_dataset | |
| import torch | |
| from peft import LoraConfig, prepare_model_for_int8_training | |
| from trl import SFTTrainer | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoTokenizer, TrainingArguments | |
| dataset_name = "timdettmers/openassistant-guanaco" | |
| dataset = load_dataset(dataset_name, split="train") | |
| model_name = "facebook/opt-350m" |
| #!/usr/bin/env python | |
| import math | |
| import matplotlib.pyplot as plt | |
| import torch | |
| import torch.nn as nn | |
| from sklearn.datasets import make_moons | |
| from torch import Tensor | |
| from tqdm import tqdm |
| from transformers import AutoTokenizer | |
| tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") | |
| text = "It 's a pre-tokenized , silly sentence !" | |
| words = text.split() | |
| encoded = tokenizer(words, is_split_into_words=True) | |
| for token, wordid in zip(encoded.tokens(), encoded.word_ids()): | |
| if wordid is not None: | |
| print(token, words[wordid]) |
