Skip to content

Instantly share code, notes, and snippets.

View benthecoder's full-sized avatar
🌊

Benedict Neo 梁耀恩 benthecoder

🌊
244 followers · 85 following
View GitHub Profile
@benthecoder
benthecoder / train.csv
Created May 11, 2022 18:23
bill_depth bill_length wing_length location mass sex ID
14.3 48.2 210 loc_2 4600 0 284
14.4 48.4 203 loc_2 4625 0 101
18.4 NA 200 loc_3 3400 0 400
14.9821138211382 47.5048780487805 NA NA 4800 0 98
18.9821138211382 38.2593070487805 217.186991869919 loc_3 5200 0 103
@benthecoder
benthecoder / bird-solution.csv
Created May 11, 2022 18:44
ID species
2 A
5 C
7 C
8 B
9 C
@benthecoder
benthecoder / slang_translator.txt
Last active September 25, 2022 03:47
source: https://github.com/rishabhverma17/sms_slang_translator/blob/master/slang.txt
{
"AFAIK": "As Far As I Know",
"AFK": "Away From Keyboard",
"ASAP": "As Soon As Possible",
"ATK": "At The Keyboard",
"ATM": "At The Moment",
"A3": "Anytime, Anywhere, Anyplace",
"BAK": "Back At Keyboard",
"BBL": "Be Back Later",
"BBS": "Be Back Soon",
@benthecoder
benthecoder / site_metadata.csv
Created October 12, 2022 19:21
source: https://tamudatathon.com/challenges/docs/baker_hughes1
We can make this file beautiful and searchable if this error is corrected: It looks like row 8 should actually have 9 columns, instead of 3 in line 7.
CUSTOMER_NAME,PLANT_NAME,LATITUDE,LONGITUDE,ELEVATION,FUEL_N2_MOL_PCT,FUEL_MW,FUEL_LHV,CO2_FUEL_RATIO
SPIFFY,SPIRITUAL-POLECAT,61.170355655416756,42.87476722769898,112.0,4.44506304774041,16.572225178958153,21514.22236545268,2.6218034758534565
NONCHALANT,NIFTY-ROOK,37.55451549722366,49.90821662683808,-29.0,1.0531449774702362,16.16609726073242,21526.470829320926,2.714869756572029
NONCHALANT,PREHISTORIC-PETREL,29.190865869410757,60.49170182347541,1552.426025390625,10.298848060446083,17.273122273669447,21494.438671718366,2.461189337194369
NONCHALANT,THERAPEUTIC-LIONFISH,13.253365033156228,76.41105642809447,867.591552734375,13.188813728960108,17.61914942302331,21485.25197916242,2.3818954537334576
SOFT,ABORIGINAL-PICULET,-68.63200204949257,66.15530078737422,1253.15283203125,7.581915824443374,16.947813109323903,21503.41743616074,2.5357355888817
SOFT,CARMINE-REINDEER,-37.9973686323425,178.14485465045027,518.8723754882812,14.604307504874159,17.7886321547886,21480.88277080532,2.3430576226374615
SOFT,IDEALISTIC-DODO,-31
@benthecoder
benthecoder / metadata.tsv
Last active March 18, 2024 09:42
title date link
compute embeddings for tweets in tweets.json 2024-03-18T08:39:57.724Z https://gist.github.com/gd3kr/c4c0687a5f7e91b1a84bcacea6500011
Eric Zhu "WEBSITE" 2024-03-18T08:39:11.512Z https://ericfzhu.com/?windows=blog%3Binspo%3Bworks
Little guide to building Large Language Models in 2024 - Google Slides 2024-03-18T07:19:41.286Z https://docs.google.com/presentation/d/1IkzESdOwdmwvPxIELYJi8--K3EZ98_cL6c5ZcLKSyVg/edit
Everything I'll forget about prompting LLMs 2024-03-18T07:12:49.834Z https://olickel.com/everything-i-know-about-prompting-llms
Codex - see similar quotes w embeddings 2024-03-18T06:11:43.723Z https://codex.ericfzhu.com/?id=2310
How to Fine-Tune an LLM Part 1: Preparing a Dataset for Instruction Tuning | alpaca_ft – Weights & Biases 2024-03-18T04:07:24.922Z https://wandb.ai/capecape/alpaca_ft/reports/How-to-fine-tune-an-LLM-Part-1-Preparing-a-Dataset-for-Instruction-Tuning--Vmlldzo1NTcxNzE2
Pix2Struct 2024-03-18T03:20:36.578Z https://huggingface.co/docs/transformers/en/model_doc/pix2s
@benthecoder
benthecoder / metadata.tsv
Created March 18, 2024 09:21
title date link
compute embeddings for tweets in tweets.json 2024-03-18T08:39:57.724Z https://gist.github.com/gd3kr/c4c0687a5f7e91b1a84bcacea6500011
Eric Zhu "WEBSITE" 2024-03-18T08:39:11.512Z https://ericfzhu.com/?windows=blog%3Binspo%3Bworks
Little guide to building Large Language Models in 2024 - Google Slides 2024-03-18T07:19:41.286Z https://docs.google.com/presentation/d/1IkzESdOwdmwvPxIELYJi8--K3EZ98_cL6c5ZcLKSyVg/edit
Everything I'll forget about prompting LLMs 2024-03-18T07:12:49.834Z https://olickel.com/everything-i-know-about-prompting-llms
Codex - see similar quotes w embeddings 2024-03-18T06:11:43.723Z https://codex.ericfzhu.com/?id=2310
How to Fine-Tune an LLM Part 1: Preparing a Dataset for Instruction Tuning | alpaca_ft – Weights & Biases 2024-03-18T04:07:24.922Z https://wandb.ai/capecape/alpaca_ft/reports/How-to-fine-tune-an-LLM-Part-1-Preparing-a-Dataset-for-Instruction-Tuning--Vmlldzo1NTcxNzE2
Pix2Struct 2024-03-18T03:20:36.578Z https://huggingface.co/docs/transformers/en/model_doc/pix2s
@benthecoder
benthecoder / gist:8212cac40e865368019c4016ec55fc02
Created March 18, 2024 09:39
This file has been truncated, but you can view the full file.
-0.03411770612001419 0.01588732749223709 -0.0009765207068994641 -0.024040192365646362 0.009449911303818226 -0.042031485587358475 0.02132655493915081 -0.013556229881942272 0.010250852443277836 0.01624595746397972 0.008493563160300255 -0.025008494034409523 0.008463677950203419 -0.030340133234858513 -0.06680089235305786 0.035432685166597366 0.021230921149253845 -0.0033980230800807476 0.0328744538128376 0.03344826400279999 0.027662359178066254 -0.019772490486502647 -0.03672375530004501 0.00968302134424448 0.023358793929219246 -0.0030782443936914206 -0.009168984368443489 0.05293384939432144 0.025845298543572426 -0.013855088502168655 -0.04757830128073692 -0.02179277502000332 -0.012061935849487782 -0.02916860766708851 -0.02842743694782257 0.014632120728492737 0.01191848423331976 0.008816330693662167 -0.010346487164497375 0.025630120187997818 0.013460595160722733 0.011523990891873837 -0.03892335295677185 0.040405694395303726 0.008374020457267761 0.05475090816617012 -0.004626332316547632 -0.03980797529220581 0.0033741
@benthecoder
benthecoder / summarize_youtube
Created March 25, 2024 05:01
import argparse
import os
from subprocess import run
import yt_dlp
from openai import OpenAI
client = OpenAI(api_key="") # YOUR KEY
@benthecoder
benthecoder / nv-embed.py
Created February 28, 2025 23:58
# NV-Embed-v2 Medical Text Embedding and Visualization
# This script demonstrates how to use NVIDIA's NV-Embed-v2 model for medical text embeddings
# and visualize the results using t-SNE
import numpy as np
import torch
import torch.nn.functional as F
from torch.nn import DataParallel
from tqdm import tqdm
from transformers import AutoModel