Does anyone use the super tiny models for anything ? Like in the 2billion or lower parameter level?
Speculative decoding[1]?
[1]: https://github.com/ggml-org/llama.cpp/blob/master/docs/specu...
Speculative decoding[1]?
[1]: https://github.com/ggml-org/llama.cpp/blob/master/docs/specu...