root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

convert : add custom attention mapping
Some checks are pending
flake8 Lint / Lint (push) Waiting to run
Details
Python Type-Check / pyright type-check (push) Waiting to run
Details

Browse Source
This commit is contained in:
Georgi Gerganov 2024-12-06 21:33:15 +02:00
parent f162d45a21
commit c5ede3849f
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 2 additions and 0 deletions
Show Stats 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 # Attention query
MODEL_TENSOR.ATTN_Q: ( MODEL_TENSOR.ATTN_Q: (
"model.layers.{bid}.self_attn.q_proj", # llama-hf nemotron olmoe olmo2 "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 "layers.{bid}.attention.wq", # llama-pth
"encoder.layer.{bid}.attention.self.query", # bert "encoder.layer.{bid}.attention.self.query", # bert
"transformer.h.{bid}.attn.q_proj", # gpt-j "transformer.h.{bid}.attn.q_proj", # gpt-j
@ -158,6 +159,7 @@ class TensorNameMap:
# Attention key # Attention key
MODEL_TENSOR.ATTN_K: ( MODEL_TENSOR.ATTN_K: (
"model.layers.{bid}.self_attn.k_proj", # llama-hf nemotron olmoe olmo2 "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 "layers.{bid}.attention.wk", # llama-pth
"encoder.layer.{bid}.attention.self.key", # bert "encoder.layer.{bid}.attention.self.key", # bert
"transformer.h.{bid}.attn.k_proj", # gpt-j "transformer.h.{bid}.attn.k_proj", # gpt-j