Sibila

- feat: Add Model.create() argument to retrieve the actual initialization params used to create the model.
- fix: Correct OpenAI's "max_tokens_limit" setting to 4096 in base_models.json, a more sensible default value for future models.
- fix: Update Model.version() formats to be simpler and simplify comparison between versions.

- feat: Add Anthropic provider.
- feat: Add chat template formats for Llama3 and Phi-3 instruct models, StableLM-2, Command-R/Plus.
- feat: Add output_fn_name property to Model, for changing the output function name in models that use a Tools/Functions API.
- feat: Better JSON/Schema decoding errors.
- fix: Don't use a string representation of the dataclass when its doc string is unset, during JSON Schema creation, to keep equivalence with Pydantic-based generation.
- fix: Workaround for MistralModel, where the Mistral API misses api_key argument/env variable when run from pytest.
- fix: Consolidate all Model class info as methods to avoid property/method() calling confusion.
- docs: Update installation instructions and include info on new Anthropic provider.
- test: Better parametrized tests for remote and local models.
- test: Add tests for new provider.

- feat: New providers: Mistral AI, Together.ai and Fireworks AI allowing access to all their chat-based models.
- feat: Model classes now support async calls with the '_async' prefix, for example extract_async(). This requires model API support: only remote models will benefit. Local models (via llama.cpp) can still be called with _async methods but do not have async IO that can run concurrently.
- feat: Add 'special' field to GenConf, allowing provider or model specific generation arguments.
- feat: All models now also accept model path/name starting with their provider names as in Models.create().
- feat: Change Model.json() to stop requiring a JSON Schema as first argument.
- fix: More robust JSON extraction for misbehaved remote models.
- fix: LlamaCppModel no longer outputting debug info when created in Jupyter notebook environment with verbose=False.
- fix: Default "gpt-4" model in 'sibila/res/base:models.json' now points to gpt-4-1106-preview, the first GPT-4 model that accepts json-object output.
- docs: Add API references for new classes and _async() methods.
- docs: Add new async example.
- test: Add new tests for new providers/model classes.

- feat: Migrate hardcoded OpenAI model entries from OpenAIModel to 'res/base_models.json'.
- feat: OpenAI now accepts unknown models using defaults from 'openai:_default' key in 'res/base_models.json'.
- feat: Support OpenAI models with a limit on max_tokens output values, like "gpt-4-turbo-preview" (input ctx_len of 128k but only up to 4k output tokens).
- feat: Auto-discover maximum ctx_len in LlamaCppModel loaded files, when 0 is passed.
- feat: Add negative int factor mode to GenConf.max_tokens setting, allowing for a percentage of model's context length.
- fix: Add coherent error exceptions when loading local and remote models.
- fix: Correct interact() error when GenConf.max_tokens=0.
- fix: Correct several chat template formats.
- test: Add many new tests for gpt-3.5/4 and llama.cpp models.
- docs: Update tips section.

- feat: Split Models factory config in two levels: base definitions in sibila/res and Models.setup() loaded definitions from user folders. These levels never mix, but a fusion of the two is used for models/formats resolution. Only in this manner can "models" folder definitions be kept clean.
- fix: Option sibila formats -u is removed as result of the two-level Models factory.
- fix: Correct delete of link entries in models.json and formats.json, which was resolving to targets (and deleting them).
- fix: Raise ValueError when trying to generate from an empty prompt in LLamaCppModel.
- fix: Update Models to check linked entries when deleting.
- fix: Update template format discovery to work in more edge cases.
- test: Add test cases for sibila CLI and LlamaCppModel.

- feat: Improve template format discovery by looking in same folder for models/formats.json.
- fix: Update legacy importlib_resources reference.
- docs: Improve text.