Add Pixtral. (#2521)

* Add Pixtral.

* More pixtral vision encoder.

* Sketch a pixtral example.

* Sketch a pixtral example.

* Better image loading.

* Support loading images embedded in safetensor files.

* Clippy fixes.

* Add the llava multimodal adapter.

* Add more of the llava bits.

* Add the pixtral config.

* More pixtral inference.

* Add the text generation bits.

* Get the example to work.

* Bugfix.

* Run some bits of the model in f32.

* Blessed version :)

* Better rope frequency computations.

* README update.

candle-transformers/src/models/pixtral/mod.rs

@@ -0,0 +1,4 @@
+pub mod llava;
+pub mod vision_model;
+
+pub use llava::{Config, Model};