← Back to context Comment by Decabytes 3 hours ago Does anyone use the super tiny models for anything ? Like in the 2billion or lower parameter level? 1 comment Decabytes Reply genpfault 17 minutes ago Speculative decoding[1]?[1]: https://github.com/ggml-org/llama.cpp/blob/master/docs/specu...
genpfault 17 minutes ago 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...