ipex backend enhancements (#272)

Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
huggingface · Sep 24, 2024 · b502dde · b502dde
1 parent ff8375e
commit b502dde
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 2 deletions.
diff --git a/examples/ipex_bert.yaml b/examples/ipex_bert.yaml
@@ -23,7 +23,7 @@ scenario:
 
 backend:
   device: cpu
-  no_weights: true
+  no_weights: false
   export: true
   torch_dtype: bfloat16
   model: bert-base-uncased
diff --git a/examples/ipex_llama.yaml b/examples/ipex_llama.yaml
@@ -32,6 +32,6 @@ scenario:
 backend:
   device: cpu
   export: true
-  no_weights: true
+  no_weights: false
   torch_dtype: bfloat16
   model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
diff --git a/optimum_benchmark/backends/ipex/utils.py b/optimum_benchmark/backends/ipex/utils.py
@@ -1,6 +1,7 @@
 TASKS_TO_IPEXMODEL = {
     "fill-mask": "optimum.intel.IPEXModelForMaskedLM",
     "text-generation": "optimum.intel.IPEXModelForCausalLM",
+    "feature-extraction": "optimum.intel.IPEXModel",
     "text-classification": "optimum.intel.IPEXModelForSequenceClassification",
     "token-classification": "optimum.intel.IPEXModelForTokenClassification",
     "question-answering": "optimum.intel.IPEXModelForQuestionAnswering",