Skip to content

Commit

Permalink
Add config for open-llama-3b-v2 (#743)
Browse files Browse the repository at this point in the history
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
  • Loading branch information
nikita-savelyevv authored Aug 7, 2024
1 parent f439d22 commit 36deb03
Showing 1 changed file with 1 addition and 0 deletions.
1 change: 1 addition & 0 deletions llm_bench/python/utils/nncf_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -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}},
Expand Down

0 comments on commit 36deb03

Please sign in to comment.