From e2b45a763bfd124b9b6bcde5f6b01cff0248075f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Stanis=C5=82aw=20Szymczyk?= Date: Mon, 24 Jun 2024 10:28:58 +0200 Subject: [PATCH] gguf-py : fix tensor groups for encoder-decoder models in gguf-dump.py --- gguf-py/scripts/gguf-dump.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/gguf-py/scripts/gguf-dump.py b/gguf-py/scripts/gguf-dump.py index 92d14d6cd..508ca8f0a 100755 --- a/gguf-py/scripts/gguf-dump.py +++ b/gguf-py/scripts/gguf-dump.py @@ -208,7 +208,9 @@ def translate_tensor_name(name): 'ssm_d': 'State space model skip connection', 'ssm_dt': 'State space model time step', 'ssm_out': 'State space model output projection', - 'blk': 'Block' + 'blk': 'Block', + 'enc': 'Encoder', + 'dec': 'Decoder', } expanded_words = [] @@ -291,6 +293,10 @@ def dump_markdown_metadata(reader: GGUFReader, args: argparse.Namespace) -> None tensor_group_name = "base" if tensor_components[0] == 'blk': tensor_group_name = f"{tensor_components[0]}.{tensor_components[1]}" + elif tensor_components[0] in ['enc', 'dec'] and tensor_components[1] == 'blk': + tensor_group_name = f"{tensor_components[0]}.{tensor_components[1]}.{tensor_components[2]}" + elif tensor_components[0] in ['enc', 'dec']: + tensor_group_name = f"{tensor_components[0]}" # Check if new Tensor Group if tensor_group_name not in tensor_groups: