Set auto dtype during model export

huggingface · Dec 12, 2024 · b547418 · b547418
1 parent 35cf1d2
commit b547418
Show file tree

Hide file tree

Showing 4 changed files with 5 additions and 5 deletions.
diff --git a/optimum/intel/openvino/modeling_base.py b/optimum/intel/openvino/modeling_base.py
@@ -592,7 +592,7 @@ def _from_transformers(
         if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
-            ov_config = OVConfig(dtype="fp32")
+            ov_config = OVConfig(dtype="auto")
 
         main_export(
             model_name_or_path=model_id,

diff --git a/optimum/intel/openvino/modeling_base_seq2seq.py b/optimum/intel/openvino/modeling_base_seq2seq.py
@@ -364,7 +364,7 @@ def _from_transformers(
         if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
-            ov_config = OVConfig(dtype="fp32")
+            ov_config = OVConfig(dtype="auto")
 
         main_export(
             model_name_or_path=model_id,

diff --git a/optimum/intel/openvino/modeling_open_clip.py b/optimum/intel/openvino/modeling_open_clip.py
@@ -247,7 +247,7 @@ def _from_transformers(
         if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
-            ov_config = OVConfig(dtype="fp32")
+            ov_config = OVConfig(dtype="auto")
 
         def fn_get_submodels(model):
             return {"model_text": model.text}
@@ -372,7 +372,7 @@ def _from_transformers(
         if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
-            ov_config = OVConfig(dtype="fp32")
+            ov_config = OVConfig(dtype="auto")
 
         def fn_get_submodels(model):
             return {"model_vision": model.visual}

diff --git a/optimum/intel/openvino/modeling_visual_language.py b/optimum/intel/openvino/modeling_visual_language.py
@@ -598,7 +598,7 @@ def _from_transformers(
         if load_in_8bit is None and not quantization_config:
             ov_config = None
         else:
-            ov_config = OVConfig(dtype="fp32")
+            ov_config = OVConfig(dtype="auto")
 
         stateful = kwargs.pop("stateful", ensure_stateful_is_available(warn=False) and use_cache)