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

initial commit for sealion support

Browse source
This commit is contained in:
bryan 2024-04-02 13:22:32 +08:00
parent f87f7b8986
commit 936289a13f
2 changed files with 5 additions and 0 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

@ -289,11 +289,13 @@ 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",
),
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",
),
MODEL_TENSOR.ROPE_FREQS: (