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/parler_tts.rs

@@ -1,3 +1,20 @@
+//! Parler Model implementation for parler_tts text-to-speech synthesis
+//!
+//! Implements a transformer-based decoder architecture for generating audio tokens
+//! from text using discrete tokens. The model converts text into audio segments
+//! using multiple codebooks of quantized audio tokens.
+//!
+//! The model architecture includes:
+//! - Multi-head attention layers for text and audio processing
+//! - Feed-forward networks
+//! - Layer normalization
+//! - Positional embeddings
+//! - Multiple codebook prediction heads
+//!
+//! The implementation follows the original parler_tts architecture while focusing
+//! on audio token generation for text-to-speech synthesis.
+//!
+
 use crate::generation::LogitsProcessor;
 use crate::models::t5;
 use candle::{IndexOp, Result, Tensor};