From 9f360fc43f742426fcfc6178d0351a8d19367e0d Mon Sep 17 00:00:00 2001 From: eaidova Date: Fri, 23 May 2025 19:35:09 +0400 Subject: [PATCH] align default int4 configuration --- notebooks/llm-chatbot/llm-chatbot.ipynb | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/notebooks/llm-chatbot/llm-chatbot.ipynb b/notebooks/llm-chatbot/llm-chatbot.ipynb index cb83b2a1fcd..7851d741bf7 100644 --- a/notebooks/llm-chatbot/llm-chatbot.ipynb +++ b/notebooks/llm-chatbot/llm-chatbot.ipynb @@ -723,8 +723,6 @@ " \"qwen2.5-0.5b-instruct\": {\"sym\": True, \"group_size\": 128, \"ratio\": 1.0},\n", " \"default\": {\n", " \"sym\": False,\n", - " \"group_size\": 128,\n", - " \"ratio\": 0.8,\n", " },\n", " }\n", "\n", @@ -733,7 +731,13 @@ " return\n", " remote_code = model_configuration.get(\"remote_code\", False)\n", " export_command_base = \"optimum-cli export openvino --model {} --task text-generation-with-past --weight-format int4\".format(pt_model_id)\n", - " int4_compression_args = \" --group-size {} --ratio {}\".format(model_compression_params[\"group_size\"], model_compression_params[\"ratio\"])\n", + " group_size = model_compression_params.get(\"group_size\")\n", + " ratio = model_compression_params.get(\"ratio\")\n", + " int4_compression_args = \"\"\n", + " if group_size is not None:\n", + " int4_compression_args += \" --group-size {}\".format(group_size)\n", + " if ratio is not None:\n", + " int4_compression_args += \" --ratio {}\".format(ratio)\n", " if model_compression_params[\"sym\"]:\n", " int4_compression_args += \" --sym\"\n", " if enable_awq.value:\n",