Awesome, glad to hear! And I am curious about the Julia experiments, but absolutely no rush 🙂
Btw I also did some quick comparisons with some other BPE implementations here: https://
github.com/rasbt/LLMs-fro
m-scratch/blob/main/ch02/02_bonus_bytepair-encoder/compare-bpe-tiktoken.ipynb
…
(I also have my own custom one that I plan to polish up and add some time…)
OPEN SOURCE
-
BPE Implementations Comparison and Julia Experiments Updates
By
–
-
Solar-powered self-hosted website with Raspberry Pi and battery
By
–
An experiment in sustainability by @dries involves a solar panel, a battery, and a @Raspberry_Pi
. Check out how he combined these materials to build a solar-powered, self-hosted website https://
bit.ly/3Yow8Ri #sustainability #solarpower #opensource -
Free Local Lite Version Available for Download
By
–
There’s a Lite version you can run locally for free
-
OSI Publishes Its Official Definition of Open Source AI
By
–
[#Article] OSAID: OSI Publishes Its Definition of Open Source AI https://actuia.com/actualite/osaid-losi-publie-sa-definition-de-lia-open-source/
…
#AI #artificialintelligence -
Community Projects: Open Source Initiative Highlighted
By
–
Not ours! These are the community's. Looks like the top one is open source:
-
Etched Oasis 500M Model Released on Hugging Face
By
–
model: https://
huggingface.co/Etched/oasis-5
00m
… -
Stack Overflow’s Impact on Code Creation and Development
By
–
What % of code was 'created by' stack overflow copypasta? Etc.
-
Smol LM v2 Released: New Open-Source Language Model
By
–
The freshly released Smol LM v2 https://
huggingface.co/collections/Hu
ggingFaceTB/smollm2-6723884218bcda64b34d7db9
… -
SmolLM v2 Releases State-of-Art Small Language Models
By
–
It’s a huge day for small models!! Super proud to release SmolLM v2 pushing the state-of-the-art performances of LLMs under 2B parameters with three sizes: 135M, 360M and 1.7B parameters. These models have been several months in the making with many lessons learned that we’ll
-
SmolLM2: Faster, Better, Cheaper Language Model
By
–
SmolLM2 – faster, better and cheaper! Intelligence is definitely too cheap to meter.