Skip to content

Instantly share code, notes, and snippets.

View mapmeld's full-sized avatar

Nick Doiron mapmeld

  • Chicago, IL
View GitHub Profile
import json
j = json.load(open('./census-reviewed.json', 'r'))
headers = None
total_vars = {
'P1_047N': 0,
'P1_063N': 0,
'P1_070N': 0,
'P2_072N': 0,
'Hisp': 0,
mapmeld /
Last active February 2, 2024 16:22
# this should run on a GPU CoLab notebook
# pip install langchain xformers transformers datasets bitsandbytes accelerate --quiet
# get access to the meta-llama models, accept license, and get a read token
hf_auth = '######'
from langchain.chains import ConversationChain
from langchain.llms import HuggingFacePipeline
from langchain.memory import ConversationSummaryBufferMemory
from langchain.prompts.prompt import PromptTemplate
mapmeld /
Created July 25, 2023 20:41
Chinese characters example



mapmeld /
Created March 12, 2023 02:21
ChatGPT on GPT-NYC type questions

Date: February 25, 2023

Questions in quotes

My comments in bold italics

Hi, I'm going to ask some questions about New York City as a new visitor, and you should respond as an expert resident.

Sure, I'm happy to help! What would you like to know about New York City?

mapmeld /
Created December 16, 2021 17:04
How to write an ML example
# All I'm looking for on an ML example:
# ! pip install name_of_library
from name_of_library import model, other_stuff
tdata = load_data_from_file() # not a built-in datasets source where I'd need to write python to add data
tdata.apply(changes) # whose dataset is so perfect we don't edit it
model.train(tdata, **explained_params)
mapmeld /
Last active December 14, 2021 03:11
Patching Models BigSci Proposal

Patching Models with New Words, People, and Events

May 6 - June 15, 2021


Once a large pre-trained language model is published, it is a snapshot of language when its corpus was collected. What are ways to update models to support new or newly-frequent terms (BIPOC), phrasing (social distancing), or people and events (Fyre Festival)? What are reliable, low-cost ways to test and benchmark these methods of updating?

Current status

mapmeld / Vanguard-Sortfix.js
Last active December 1, 2021 16:43
Sort stocks by percent change or my holdings change
Generally, don't run random JS in your browser console, especially on financial sites, but here we are
By default this sorts by Percent Change. If you uncomment the next line it sorts by myDelta (price x your shares)
- I'm not affiliated with Vanguard or any licensed financial advisor or tax preparer. I don't have a clue what's going on with your finances.
- The script assumes you did NOT trade today; it uses today's change and current shares
- Delta-sort does not handle penny stocks as well because the UI says 0.01 and we reverse-engineer from current balance
let sortRule = 'pct';
mapmeld /
Created July 9, 2021 12:40
Add text file task to T5
"train": "gs://BUCKET/train_lines.txt",
"validation": "gs://BUCKET/validation_lines.txt",
mapmeld /
Last active January 4, 2021 16:01
Bangla Benchmark runs


Can these scores be improved? YES!

Rerunning with more training data, more epochs of training, or using other libraries to set a learning rate / other hyperparameters before training.

  • Experimenting with epochs - when I doubled the number of epochs, MuRIL improves only slightly (69.5->69.7 on one task)

The point of a benchmark is to run these models through a reasonable and identical process; you can tweak hyperparameters on any model to improve results.

mapmeld /
Last active October 22, 2020 15:38