Mistralrs

What's Changed
* Add and update template READMEs by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/405
* Improve Rust crates docs by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/406
* Expose phi3v loader and remove unused deps by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/408
* Support GGUF Mixtral format where experts are in one tensor by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/355
* Refactor with normal loading metadata for vision models by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/409
* Phi 3 vision ISQ support by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/410
* Remove causal masks cache by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/412
* Fix: use new slice_assign by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/415
* Fix Phi-3 GGUF by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/414
* Implement gpt2 (BPE) GGUF tokenizer conversion by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/397
* Support chat template from GGUF by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/416
* Expose API to specify dtype during loading by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/417
* Lock candle version to commit by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/419
* Bump version to 0.1.17 by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/420


**Full Changelog**: https://github.com/EricLBuehler/mistral.rs/compare/v0.1.16...v0.1.17

Summary
- Various fixes
- Excellent work on refactoring by polarathene
- First vision model: Phi 3 vision

What's Changed
* Implement the Phi 3 vision model by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/351
* Bump version again to 0.1.15 by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/390
* Add docs for installing huggingface-cli by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/391
* Fix metal loading issue by loading sequentially by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/394
* Fix logging in gguf and ggml by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/399
* Add fused bias linear layer with cublaslt by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/400
* docs: Resolve CI lints on docs by polarathene in https://github.com/EricLBuehler/mistral.rs/pull/401
* Refactor: GGUF metadata tokenizer by polarathene in https://github.com/EricLBuehler/mistral.rs/pull/389
* Add `Nonzero` layer by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/402
* Bump version to 0.1.16 by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/404


**Full Changelog**: https://github.com/EricLBuehler/mistral.rs/compare/v0.1.15...v0.1.16

What's Changed
* Patch incorrect unwrap and bump version by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/383


**Full Changelog**: https://github.com/EricLBuehler/mistral.rs/compare/v0.1.14...v0.1.15

What's Changed
* Improve docs for loading `gguf` purely locally by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/371
* Fix message with chat template by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/374
* Fix tokenizer write on read only file system by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/373
* Manual subtyping for u32 in GGUF max seq len by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/376
* refactor: DRY `varbuilder_utils.rs` by polarathene in https://github.com/EricLBuehler/mistral.rs/pull/364
* Support multiple GGUF files by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/379
* Organize normal loading metadata by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/381
* Bump version 0.1.13 -> 0.1.14 by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/382


**Full Changelog**: https://github.com/EricLBuehler/mistral.rs/compare/v0.1.13...v0.1.14

What's Changed
* Prepare to accept multiple model types by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/369
* Fix chat template and F16/BF16 CUDA GEMM when RUST_BACKTRACE by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/370


**Full Changelog**: https://github.com/EricLBuehler/mistral.rs/compare/v0.1.12...v0.1.13

What's Changed
* Add an example by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/357
* Fix no auth token for local loading by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/360
* fix: Ensure committed files are normalized to LF by polarathene in https://github.com/EricLBuehler/mistral.rs/pull/361
* Fix unauth check by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/362
* Allow default unigram unk token for GGUF by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/363
* Disable cublaslt if using f16 kernels by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/359
* refactor: GGUF + GGML Loaders with `ModelKind` by polarathene in https://github.com/EricLBuehler/mistral.rs/pull/356
* Clamp n device layers to n model layers by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/367
* Bump version to 0.1.12 by EricLBuehler in https://github.com/EricLBuehler/mistral.rs/pull/368


**Full Changelog**: https://github.com/EricLBuehler/mistral.rs/compare/v0.1.11...v0.1.12