Gguf-llama

Another significant change in functioning, until version 0.1.0 fix versions don't guarantee api consistency, so treat each version as individual version. And of course this is alpha a lot thigs are still being polished.

in this version we're adjusting mostly documentation after last update

What's Changed
* Develop by laelhalawani in https://github.com/laelhalawani/gguf_llama/pull/11


**Full Changelog**: https://github.com/laelhalawani/gguf_llama/compare/v0.0.15...v0.0.16

Another significant change in functioning, until version 0.1.0 fix versions don't guarantee api consistency, so treat each version as individual version. And of course this is alpha a lot thigs are still being polished.

With this version we removed input token limit from initialization of the model, it can be set by a dedicated method now as additional guardrail.