Skip to content

Instantly share code, notes, and snippets.

View wesyoung's full-sized avatar
🎯
Focusing

wes wesyoung

🎯
Focusing
143 followers · 156 following
View GitHub Profile
@karpathy
karpathy / llm-wiki.md
Created April 4, 2026 16:25
llm-wiki

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@ruvnet
ruvnet / *DeepSeek-uncensored.md
Last active February 27, 2026 17:04
Deploying and Fine-Tuning an Uncensored DeepSeek R1 Distill Model on Google Cloud

DeepSeek R1 Distill: Complete Tutorial for Deployment & Fine-Tuning

This guide shows how to deploy an uncensored DeepSeek R1 Distill model to Google Cloud Run with GPU support and how to perform a basic, functional fine-tuning process. The tutorial is split into:

  1. Environment Setup
  2. FastAPI Inference Server
  3. Docker Configuration
  4. Google Cloud Run Deployment
  5. Fine-Tuning Pipeline (Cold Start, Reasoning RL, Data Collection, Final RL Phase)
@wesyoung
wesyoung / gist:b28510ffc7ccd7e5cdd8753213a49de3
Created March 30, 2024 13:36 — forked from mberman84/gist:c95d69263d9c2ceb7d56cf336f13ae02
AutoGen + MemGPT Code
import os
import autogen
import memgpt.autogen.memgpt_agent as memgpt_autogen
import memgpt.autogen.interface as autogen_interface
import memgpt.agent as agent
import memgpt.system as system
import memgpt.utils as utils
import memgpt.presets as presets
import memgpt.constants as constants
import memgpt.personas.personas as personas
@mberman84
mberman84 / gist:c95d69263d9c2ceb7d56cf336f13ae02
Created October 26, 2023 19:03
AutoGen + MemGPT Code
import os
import autogen
import memgpt.autogen.memgpt_agent as memgpt_autogen
import memgpt.autogen.interface as autogen_interface
import memgpt.agent as agent
import memgpt.system as system
import memgpt.utils as utils
import memgpt.presets as presets
import memgpt.constants as constants
import memgpt.personas.personas as personas
@ih2502mk
ih2502mk / list.md
Last active April 19, 2026 19:52
Quantopian Lectures Saved
@mutin-sa
mutin-sa / Top_Public_Time_Servers.md
Last active April 18, 2026 10:15
List of Top Public Time Servers

Google Public NTP [AS15169]:

time.google.com

time1.google.com

time2.google.com

time3.google.com

@mutin-sa
mutin-sa / Top_Public_Recursive_Name_Servers.md
Last active April 19, 2026 14:27
List of Top Public Recursive Name Servers

DNS:

IPv4 Addr IPv6 Addr ASn Political Region Loc Svc Org
8.8.8.8 2001:4860:4860::8888 AS15169 US Worldwide (Anycast) Google Public DNS Google
8.8.4.4 2001:4860:4860::8844 AS15169 US Worldwide (Anycast) Google Public DNS Google
1.1.1.1 2606:4700:4700::1111 AS13335 US Worldwide (Anycast) Cloudflare-DNS Cloudflare/APNIC
1.0.0.1 2606:4700:4700::1001 AS13335 US Worldwide (Anycast) Cloudflare-DNS Cloudflare/APNIC
95.85.95.85 2a03:90c0:999d::1 AS199524 EU *W
@gssbzn
gssbzn / yarm.config
Last active October 30, 2018 18:57
Elastic Beanstalk Rails+Webpacker extension
# Copyright 2018 SwiftComply.com
commands:
01_node_install:
test: "[ `node --version` != 'v8.10.0' ]"
command: "curl --silent --location https://rpm.nodesource.com/setup_8.x | sudo bash -"
02_yarn_repo:
test: "[ ! -f /etc/yum.repos.d/yarn.repo ]"
command: "curl --silent --location https://dl.yarnpkg.com/rpm/yarn.repo | sudo tee /etc/yum.repos.d/yarn.repo"
03_yarn_install:
test: "[ ! -x /usr/bin/yarn ]"
@vgpena
vgpena / loadModel.py
Last active November 17, 2020 16:39
Basic text classification with Keras and TensorFlow
import json
import numpy as np
import keras
import keras.preprocessing.text as kpt
from keras.preprocessing.text import Tokenizer
from keras.models import model_from_json
# we're still going to use a Tokenizer here, but we don't need to fit it
tokenizer = Tokenizer(num_words=3000)
# for human-friendly printing
@adamkusey
adamkusey / securitai-lstm-model.py
Last active June 2, 2018 23:10
SecuritAI LSTM RNN Model
model = Sequential()
model.add(Embedding(num_words, 32, input_length=max_log_length))
# Prevent overfitting using dropout method of regularization
model.add(Dropout(0.5))
model.add(LSTM(64, recurrent_dropout=0.5))
model.add(Dropout(0.5))
# Condense to single binary output value
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# Training set automatically split 75/25 to check validation loss/accuracy at each epoch