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/llava/mod.rs

@@ -279,7 +279,7 @@ impl LLaVA {
                             (),
                         ))?
                     } else {
-                        todo!("not implemented in original python LLaVA yet")
+                        bail!("not implemented in original python LLaVA yet")
                     };
                     let new_image_feature = if mm_patch_merge_type.contains("unpad") {
                         let new_image_feature = new_image_feature