add qwen3.5 gguf

This commit is contained in:
jhqxxx
2026-03-14 19:27:01 +08:00
parent 4d544ab68f
commit aad0e62151
15 changed files with 656 additions and 241 deletions
+2
View File
@@ -7,6 +7,8 @@ use candle_nn::{
embedding, layer_norm, linear_b, linear_no_bias, ops::sigmoid, rms_norm,
};
pub mod gguf;
use crate::{
position_embed::rope::{RoPE, apply_rotary_pos_emb, apply_rotary_pos_emb_roformer},
utils::tensor_utils::{prepare_causal_attention_mask, repeat_kv},