Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

convert : remove AWQ remnants (#8320)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-07-05 10:15:36 +03:00 committed by GitHub
parent 2cccbaa008
commit 148ec970b6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
convert_hf_to_gguf.py
View File

@ -2445,7 +2445,7 @@ class Gemma2Model(Model):
raise ValueError("query_pre_attn_scalar must be equal to n_embd / n_head") raise ValueError("query_pre_attn_scalar must be equal to n_embd / n_head")
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]: def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
del bid # unusem del bid # unused
# lm_head is not used in llama.cpp, while autoawq will include this tensor in model # lm_head is not used in llama.cpp, while autoawq will include this tensor in model
# To prevent errors, skip loading lm_head.weight. # To prevent errors, skip loading lm_head.weight.
@ -3225,10 +3225,6 @@ def parse_args() -> argparse.Namespace:
"--vocab-only", action="store_true", "--vocab-only", action="store_true",
help="extract only the vocab", help="extract only the vocab",
) )
parser.add_argument(
"--awq-path", type=Path, default=None,
help="Path to scale awq cache file",
)
parser.add_argument( parser.add_argument(
"--outfile", type=Path, "--outfile", type=Path,
help="path to write to; default: based on input. {ftype} will be replaced by the outtype.", help="path to write to; default: based on input. {ftype} will be replaced by the outtype.",
@ -3306,19 +3302,6 @@ def main() -> None:
dir_model = args.model dir_model = args.model
if args.awq_path:
sys.path.insert(1, str(Path(__file__).parent / 'awq-py'))
from awq.apply_awq import add_scale_weights # type: ignore[import-not-found]
tmp_model_path = args.model / "weighted_model"
dir_model = tmp_model_path
if tmp_model_path.is_dir():
logger.info(f"{tmp_model_path} exists as a weighted model.")
else:
tmp_model_path.mkdir(parents=True, exist_ok=True)
logger.info("Saving new weighted model ...")
add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path))
logger.info(f"Saved weighted model at {tmp_model_path}.")
if not dir_model.is_dir(): if not dir_model.is_dir():
logger.error(f'Error: {args.model} is not a directory') logger.error(f'Error: {args.model} is not a directory')
sys.exit(1) sys.exit(1)