Pixilab
Home › Companies › Show HN launch › Trained Tiny Tales GPT(30M model)from scratch and deployed in $15

Trained Tiny Tales GPT(30M model)from scratch and deployed in $15

Show HN: Trained Tiny Tales GPT(30M model)from scratch and deployed in $15

Operating in show hn launch, Trained Tiny Tales GPT(30M model)from scratch and deployed in $15 operates.

Profile

For the last few weeks, I have been working on training an LLM from scratch and deploying it in production on Google Cloud Platform. Finally, I trained a 30 million parameter model on 1 billion tokens and deployed it as a web service. You can access the LLM using this site - https://kunalmishra.infoThe following steps were taken to build Tiny Tales GPT 1. Downloaded and preprocessed 8GB of dataset using multiprocessing library. 2. Tokenized the data using byte pair encoding to create 1 billion tokens sharded in different bin files. 3. Defined a training setup and trained the model on a small version of the LLaMA model architecture with 30 million parameters. 4. The training was done using Di

Within the show hn launch space, the company focuses on its core offering rather than a broad product line.

The company is listed at the Show HN launch stage of development.

SectorShow HN launch
StageShow HN launch

Website: kunalmishra.info

Browse related

Full contact details are available to registered Pixilab members.
Create a free account