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

llama : add SEA-LION support (#6448)

Browse source 
* initial commit for sealion support

* add sealion support

* minor fix

* q/k ln and pos_embd only if required

* Apply suggestions from code review

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

* minor : clear whitespaces

---------

Co-authored-by: bryan <bryansiow@aisingapore.org>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
bryanSwk 2024-04-04 02:05:10 +08:00 • committed by GitHub
parent 9f62c0173d
commit bb43cf7e9d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 65 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
gguf-py/gguf/constants.py
View file

@ -367,6 +367,9 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_ACT,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.POS_EMBD,
],
MODEL_ARCH.GPTJ: [
MODEL_TENSOR.TOKEN_EMBD,

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

@ -285,11 +285,13 @@ class TensorNameMap:
MODEL_TENSOR.ATTN_Q_NORM: (
"language_model.encoder.layers.{bid}.self_attention.q_layernorm",
"model.layers.{bid}.self_attn.q_layernorm", # persimmon
"transformer.blocks.{bid}.attn.q_ln", # sea-lion
),
MODEL_TENSOR.ATTN_K_NORM: (
"language_model.encoder.layers.{bid}.self_attention.k_layernorm",
"model.layers.{bid}.self_attn.k_layernorm", # persimmon
"transformer.blocks.{bid}.attn.k_ln", # sea-lion
),
MODEL_TENSOR.ROPE_FREQS: (