From 36deb03a442cacfccb65a2ef1e1d16c616f07eea Mon Sep 17 00:00:00 2001 From: Nikita Savelyev Date: Wed, 7 Aug 2024 16:01:51 +0200 Subject: [PATCH] Add config for open-llama-3b-v2 (#743) Add config for `open-llama-3b-v2` model because it is present in optimum-intel https://github.com/huggingface/optimum-intel/blame/main/optimum/intel/openvino/configuration.py#L80 --- llm_bench/python/utils/nncf_utils.py | 1 + 1 file changed, 1 insertion(+) diff --git a/llm_bench/python/utils/nncf_utils.py b/llm_bench/python/utils/nncf_utils.py index 01d0dd95b3..52f74173fa 100644 --- a/llm_bench/python/utils/nncf_utils.py +++ b/llm_bench/python/utils/nncf_utils.py @@ -58,6 +58,7 @@ def get_compressed_path(output_dir: str, base_precision, option: str): "chatglm2-6b": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 128, "ratio": 0.72}, "qwen-7b-chat": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 128, "ratio": 0.6}, "open-llama-3b": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 64, "ratio": 1.0, "all_layers": True}, + "open-llama-3b-v2": {"mode": nncf.CompressWeightsMode.INT4_ASYM, "group_size": 64, "ratio": 1.0}, "falcon-7b-instruct": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 64, "all_layers": True}, "orca-mini-3b": {"mode": nncf.CompressWeightsMode.INT4_SYM, "group_size": 64, "all_layers": True, "dataset": {"name": "wikitext,wikitext-2-v1,train[:1000],text", "awq": False}},