Updating HF_MODEL_QUANTIZE (awslabs#17)

jinyoung-lim · Jun 22, 2023 · f6e1908 · f6e1908
1 parent c64e946
commit f6e1908
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/examples/huggingface/huggingface-large-model-inference.ipynb b/examples/huggingface/huggingface-large-model-inference.ipynb
@@ -122,7 +122,7 @@
     "    'HF_MODEL_ID':'EleutherAI/gpt-neox-20b',\n",
     "    'HF_TASK':'text-generation',\n",
     "    'SM_NUM_GPUS':'4',\n",
-    "    'HF_MODEL_QUANTIZE':'true'\n",
+    "    'HF_MODEL_QUANTIZE':'bitsandbytes'\n",
     "}\n",
     "\n",
     "model = HuggingFaceModel(\n",