tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-19 22:36:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

convert : add custom attention mapping

Browse Source
This commit is contained in:
Georgi Gerganov
2024-12-06 21:33:15 +02:00
parent f162d45a21
commit c5ede3849f
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -146,6 +146,7 @@ class TensorNameMap:
# Attention query
MODEL_TENSOR.ATTN_Q: (
"model.layers.{bid}.self_attn.q_proj", # llama-hf nemotron olmoe olmo2
"model.layers.{bid}.self_attn.q_proj_no_perm", # llama-custom
"layers.{bid}.attention.wq", # llama-pth
"encoder.layer.{bid}.attention.self.query", # bert
"transformer.h.{bid}.attn.q_proj", # gpt-j
@@ -158,6 +159,7 @@ class TensorNameMap:
# Attention key
MODEL_TENSOR.ATTN_K: (
"model.layers.{bid}.self_attn.k_proj", # llama-hf nemotron olmoe olmo2
"model.layers.{bid}.self_attn.k_proj_no_perm", # llama-custom
"layers.{bid}.attention.wk", # llama-pth
"encoder.layer.{bid}.attention.self.key", # bert
"transformer.h.{bid}.attn.k_proj", # gpt-j