Documentation Pass for Models (#2617)

* links in chinese_clip

* links for clip model

* add mod docs for flux and llava

* module doc for MMDIT and MIMI

* add docs for a few more modesl

* mod docs for bert naser and beit

* add module docs for convmixer colpali codegeex and chatglm

* add another series of moddocs

* add  fastvit-llama2_c

* module docs mamba -> mobileone

* module docs from moondream-phi3

* mod docs for quantized and qwen

* update to yi

* fix long names

* Update llama2_c.rs

* Update llama2_c_weights.rs

* Fix the link for mimi + tweaks

---------

Co-authored-by: Laurent Mazare <laurent.mazare@gmail.com>

candle-transformers/src/models/quantized_mixformer.rs

@@ -1,3 +1,16 @@
+//! Module containing quantized MixFormer model implementation.
+//!
+//! MixFormer is an efficient transformer variant for text generation that uses
+//! mixture-of-experts and parallel attention/feed-forward blocks.
+//! This implementation provides quantization for reduced memory usage.
+//!
+//! Key features:
+//! - Parallel attention and feed-forward computation
+//! - Rotary positional embeddings
+//! - Optional key-value caching
+//! - Support for 8-bit quantization
+//!
+
 use crate::quantized_nn::{layer_norm, linear, Linear};
 pub use crate::quantized_var_builder::VarBuilder;
 use candle::{DType, Device, IndexOp, Module, Result, Tensor, D};