Llm-anyscale-endpoints

- New models: `meta-llama/Llama-3-8b-chat-hf` and `meta-llama/Llama-3-70b-chat-hf`. [8](https://github.com/simonw/llm-anyscale-endpoints/issues/8)

- Three new models: `google/gemma-7b-it`, `mistralai/Mixtral-8x22B-Instruct-v0.1` and `mlabonne/NeuralHermes-2.5-Mistral-7B`.
- New `llm anyscale-endpoints refresh` command for refreshing the list of models without needing to upgrade the plugin. [7](https://github.com/simonw/llm-anyscale-endpoints/issues/7)

- Three new models: `"mistralai/Mixtral-8x7B-Instruct-v0.1"`, `"Open-Orca/Mistral-7B-OpenOrca"` and `"HuggingFaceH4/zephyr-7b-beta"`. [6](https://github.com/simonw/llm-anyscale-endpoints/issues/6)

- Added the `mistralai/Mistral-7B-Instruct-v0.1` model. Thanks, [Nikita Zavgorodnii](https://github.com/nikitajz). [#4](https://github.com/simonw/llm-anyscale-endpoints/pull/4)

- Support for the `codellama/CodeLlama-34b-Instruct-hf` model - [Code Llama](https://ai.meta.com/blog/code-llama-large-language-model-coding/) is a new model from Meta AI that specializes in code. [#2](https://github.com/simonw/llm-anyscale-endpoints/issues/2)

- Initial release. Adds support to LLM for three models hosted by [Anyscale Endpoints](https://endpoints.anyscale.com/): `meta-llama/Llama-2-7b-chat-hf`, `meta-llama/Llama-2-13b-chat-hf` and `meta-llama/Llama-2-70b-chat-hf`. [#1](https://github.com/simonw/llm-anyscale-endpoints/issues/1)