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

llama : add StarCoder2 support (#5795)

Browse source 
* Add support for starcoder2

* handle rope type

* skip rope freq and rotary embeddings from being serialized

* resolve comments

* Update llama.cpp

* remove redundant changes

* handle `rope-theta`

* llama : change starcoder2 rope type

* address comment

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Sourab Mangrulkar 2024-03-02 01:00:46 +05:30 • committed by GitHub
parent 38d16b1426
commit c29af7e225
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 229 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
gguf-py/gguf/tensor_mapping.py
View file

@ -210,6 +210,7 @@ class TensorNameMap:
"model.layers.layers.{bid}.mlp.up_proj", # plamo
"model.layers.{bid}.feed_forward.w3", # internlm2
"encoder.layers.{bid}.mlp.fc11", # nomic-bert
"model.layers.{bid}.mlp.c_fc", # starcoder2
),
MODEL_TENSOR.FFN_UP_EXP: (
@ -256,6 +257,7 @@ class TensorNameMap:
"model.layers.layers.{bid}.mlp.down_proj", # plamo
"model.layers.{bid}.feed_forward.w2", # internlm2
"encoder.layers.{bid}.mlp.fc2", # nomic-bert
"model.layers.{bid}.mlp.c_proj", # starcoder2
),
MODEL_TENSOR.FFN_DOWN_EXP: (