From f6793491b5af6da75edad34d6f503ef86d31b09f Mon Sep 17 00:00:00 2001 From: "Nam D. Tran" <42194884+namtranase@users.noreply.github.com> Date: Wed, 27 Dec 2023 22:39:45 +0700 Subject: llama : add AWQ for llama, llama2, mpt, and mistral models (#4593) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * update: awq support llama-7b model * update: change order * update: benchmark results for llama2-7b * update: mistral 7b v1 benchmark * update: support 4 models * fix: Readme * update: ready for PR * update: readme * fix: readme * update: change order import * black * format code * update: work for bot mpt and awqmpt * update: readme * Rename to llm_build_ffn_mpt_awq * Formatted other files * Fixed params count * fix: remove code * update: more detail for mpt * fix: readme * fix: readme * update: change folder architecture * fix: common.cpp * fix: readme * fix: remove ggml_repeat * update: cicd * update: cicd * uppdate: remove use_awq arg * update: readme * llama : adapt plamo to new ffn ggml-ci --------- Co-authored-by: Trần Đức Nam Co-authored-by: Le Hoang Anh Co-authored-by: Georgi Gerganov --- convert.py | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'convert.py') diff --git a/convert.py b/convert.py index 1f0c4f2f..c3f3fc0a 100755 --- a/convert.py +++ b/convert.py @@ -1187,6 +1187,7 @@ def main(args_in: list[str] | None = None) -> None: # We currently only support Q8_0 output on little endian systems. output_choices.append("q8_0") parser = argparse.ArgumentParser(description="Convert a LLaMa model to a GGML compatible file") + parser.add_argument("--awq-path", type=Path, help="Path to scale awq cache file", default=None) parser.add_argument("--dump", action="store_true", help="don't convert, just show what's in the model") parser.add_argument("--dump-single", action="store_true", help="don't convert, just show what's in a single model file") parser.add_argument("--vocab-only", action="store_true", help="extract only the vocab") @@ -1200,6 +1201,19 @@ def main(args_in: list[str] | None = None) -> None: parser.add_argument("--padvocab", action="store_true", help="add pad tokens when model vocab expects more than tokenizer metadata provides") args = parser.parse_args(args_in) + if args.awq_path: + sys.path.insert(1, str(Path(__file__).parent / 'awq-py')) + from awq.apply_awq import add_scale_weights + tmp_model_path = args.model / "weighted_model" + if tmp_model_path.is_dir(): + print(f"{tmp_model_path} exists as a weighted model.") + else: + tmp_model_path.mkdir(parents=True, exist_ok=True) + print("Saving new weighted model ...") + add_scale_weights(str(args.model), str(args.awq_path), str(tmp_model_path)) + print(f"Saved weighted model at {tmp_model_path}.") + args.model = tmp_model_path + if args.dump_single: model_plus = lazy_load_file(args.model) do_dump_model(model_plus) -- cgit v1.2.3