FOI fruit machine
This is not quite a one armed bandit, but the closest I could get in a Gradio space π. https://huggingface.co/spaces/HMC83/request-generator Itβs running one of the OLMo fine-tunes at the moment....
This is not quite a one armed bandit, but the closest I could get in a Gradio space π. https://huggingface.co/spaces/HMC83/request-generator Itβs running one of the OLMo fine-tunes at the moment....
I recently trained a ~645M parameter LLM from the ground up. This was by far the largest model that I have attempted to create to date. I wanted to train a βgood enoughβ base model that was fully m...
ΠΡΠΊΠ°ΠΌ Π΄Π° Π·Π°ΠΏΠΈΡΠ° Π·Π° ΠΌΠ°Π»ΠΊΠΈΡΠ΅ Π½Π΅ΡΠ°. ΠΡΡΠ½Π°Ρ ΡΠ΅ ΠΊΡΠΌ ΡΠΎΠ·ΠΈ Π΅Π·ΠΈΠΊ, ΠΊΠΎΠΉΡΠΎ Π±ΡΡ ΠΈΠ·ΠΎΡΡΠ°Π²ΠΈΠ»Π°. Π‘ Π΅Π·ΠΈΠΊΠ° ΡΠ΅ Π²ΡΡΡΠ° ΠΈ Π΅Π½ΡΡΡΠΈΠ°Π·ΠΌΡΡ. ΠΡΠΌΠ° Π±ΡΡΠ·ΠΈΠ½Π°ΡΠ° ΠΈ ΡΠΎΠΏΠ»ΠΈΠ½Π°ΡΠ° Π½Π° ΡΠΎΠ΄Π½ΠΈΡ Π΅Π·ΠΈΠΊ, Π½ΠΎ ΠΈΠΌΠ° Π½ΠΎΠ²ΠΈ Π΄ΡΠΌΠΈ ΠΈ Π½ΠΎΠ² Π½Π°ΡΠΈΠ½ Π΄Π° Π²ΠΈΠ΄Ρ Π½Π΅ΡΠ°Ρ...
This week I wanted to explore whether a model that is smaller than the average Android app could outperform billion-parameter LLMs on a specialised task. To test this out, I trained a 22 million pa...
Objective Travel on as many different types of public transport as possible within a 12β―hour window, starting and finishing in the same location. Ground Rules For the purposes of this challenge, I...
At the start of the year I scraped data from over 800,000 FOI requests from WhatDoTheyKnow to look for patterns in the data. This sent me down a number of rabbit holes, including experiments with a...