vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add CodeShell support (#5016)

Browse source 
* llama: add codeshell support

* llama.cpp: fix codeshell with NeoX rope

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
chiranko 2024-01-19 17:07:27 +08:00 • committed by GitHub
parent 993fba8180
commit 2b3b999cac
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 268 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
gguf-py/gguf/tensor_mapping.py
View file

@ -154,6 +154,7 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.rotary_emb.inv_freq", # llama-hf
"layers.{bid}.attention.inner_attention.rope.freqs", # llama-pth
"model.layers.layers.{bid}.self_attn.rotary_emb.inv_freq", # plamo
"transformer.h.{bid}.attn.rotary_emb.inv_freq", # codeshell
),
# Feed-forward norm