Add support for Llama 3.1 (#2359)

* Add Llama 3.1 rope

* Clippy

* Format

* Clippy

* Add support for multiple eos tokens:

* Untagged either

* Remove either dep and fix settings.json

* Make the max positional embeddings configurable

candle-transformers/src/models/encodec.rs

@@ -571,7 +571,7 @@ impl<'a> Layer<'a> {
     }
 
     fn next(&mut self) -> VarBuilder {
-        let vb = self.vb.pp(&self.cnt.to_string());
+        let vb = self.vb.pp(self.cnt.to_string());
         self.cnt += 1;
         vb
     }