From f689ce5d39c6f1475dfc71503288ea2905c8f685 Mon Sep 17 00:00:00 2001 From: zachcp Date: Fri, 15 Nov 2024 02:30:15 -0500 Subject: 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 --- candle-transformers/src/models/quantized_rwkv_v5.rs | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'candle-transformers/src/models/quantized_rwkv_v5.rs') diff --git a/candle-transformers/src/models/quantized_rwkv_v5.rs b/candle-transformers/src/models/quantized_rwkv_v5.rs index c41d7b4e..cc5204bf 100644 --- a/candle-transformers/src/models/quantized_rwkv_v5.rs +++ b/candle-transformers/src/models/quantized_rwkv_v5.rs @@ -1,3 +1,20 @@ +//! RWKV v5 model implementation with quantization support. +//! +//! RWKV v5 is an attention-free language model optimized for efficiency. +//! This implementation provides quantization for reduced memory and compute. +//! +//! Key characteristics: +//! - Linear attention mechanism +//! - GroupNorm layer normalization +//! - Time-mixing layers +//! - State-based sequential processing +//! - Support for 8-bit quantization +//! +//! References: +//! - [RWKV Model](https://github.com/BlinkDL/RWKV-LM) +//! - [RWKV v5 Architecture](https://www.rwkv.com/v5) +//! + use crate::{ quantized_nn::{layer_norm, linear_no_bias as linear, Embedding, Linear}, quantized_var_builder::VarBuilder, -- cgit v1.2.3