gpt-tokenizer
bpe-encoder-php
gpt-tokenizer | bpe-encoder-php | |
---|---|---|
1 | 1 | |
383 | 5 | |
- | - | |
3.3 | 2.6 | |
10 days ago | about 1 year ago | |
TypeScript | PHP | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
gpt-tokenizer
-
I wrote a tokenizer for LLaMA that runs inside the browser
There are more differences between GPT2 tokenizer and LLaMA tokenizer than only the vocab and merge data. It would take me some time to do implement a GPT2 tokenizer, and there are already good alternatives for those, so it wouldn't make sense to put time into making another one. For example, this library contains a GPT2 tokenizer: https://github.com/niieani/gpt-tokenizer
bpe-encoder-php
-
BPE (Byte-Pair Encoding) Implementation In PHP
Just released a BPE (motivated from GPT-2 python encoder.py) implementation in PHP. https://github.com/sajjadh47/bpe-encoder-php
What are some alternatives?
Lobe Chat - LobeChat is a open-source, extensible (Function Calling), high-performance chatbot framework.It supports one-click free deployment of your private ChatGPT/LLM web application.
RWKV-LM - RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
openai-caching-proxy-worker - caching proxy for OpenAI API, deployable as a Cloudflare Worker
gpt-neo - An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
auto-gpt-web - Set Your Goals, AI Achieves Them.
Discord-AI-Chatbot - This Discord chatbot is incredibly versatile. Powered incredibly fast Groq API
llama-tokenizer-js - JS tokenizer for LLaMA and LLaMA 2