tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
5 changed files with 65 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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: (