summaryrefslogtreecommitdiff
path: root/gguf-py/gguf/tensor_mapping.py
diff options
context:
space:
mode:
authorbryanSwk <93190252+bryanSwk@users.noreply.github.com>2024-04-04 02:05:10 +0800
committerGitHub <noreply@github.com>2024-04-03 21:05:10 +0300
commitbb43cf7e9d86d69ffd9c7f008f75db890a35b45a (patch)
tree4abfed45ae4e8c2dd59c0a49df4c0f0cf801515e /gguf-py/gguf/tensor_mapping.py
parent9f62c0173d964972849251c8ad12fc356f5b7896 (diff)
llama : add SEA-LION support (#6448)
* 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>
Diffstat (limited to 'gguf-py/gguf/tensor_mapping.py')
-rw-r--r--gguf-py/gguf/tensor_mapping.py2
1 files changed, 2 insertions, 0 deletions
diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py
index 93a5a455..345b1b0c 100644
--- a/gguf-py/gguf/tensor_mapping.py
+++ b/gguf-py/gguf/tensor_mapping.py
@@ -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: (