Skip to content

Fix qa evaluation data classification policy #1962

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yoavkatz merged 2 commits into from
Feb 9, 2026
Merged

Fix qa evaluation data classification policy #1962

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2a73943
Fix data classification policy warning in qa_evaluation.py
yoavkatz Jan 18, 2026
3d3b21d
Replace deprecated torch_dtype with dtype parameter
yoavkatz Jan 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions examples/qa_evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
template="templates.qa.open",
split="test",
format="formats.chat_api",
data_classification_policy=["public"],
)

model = CrossProviderInferenceEngine(model="SmolLM2-1.7B-Instruct", provider="hf-local")
Expand Down
12 changes: 6 additions & 6 deletions src/unitxt/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -728,9 +728,9 @@ def _get_model_args(self) -> Dict[str, Any]:
args["quantization_config"] = quantization_config
elif self.use_fp16:
if self.device == torch.device("mps"):
args["torch_dtype"] = torch.float16
args["dtype"] = torch.float16
else:
args["torch_dtype"] = torch.bfloat16
args["dtype"] = torch.bfloat16

# We do this, because in some cases, using device:auto will offload some weights to the cpu
# (even though the model might *just* fit to a single gpu), even if there is a gpu available, and this will
Expand Down Expand Up @@ -937,7 +937,7 @@ def _init_model(self):

self.model = LlavaForConditionalGeneration.from_pretrained(
self.model_name,
torch_dtype=self._get_torch_dtype(),
dtype=self._get_torch_dtype(),
low_cpu_mem_usage=self.low_cpu_mem_usage,
device_map=self.device_map,
)
Expand Down Expand Up @@ -1108,7 +1108,7 @@ def _init_model(self):
trust_remote_code=True,
device_map=self.device_map,
low_cpu_mem_usage=self.low_cpu_mem_usage,
torch_dtype=self._get_torch_dtype(),
dtype=self._get_torch_dtype(),
)
self.model = self.model.to(
dtype=self._get_torch_dtype()
Expand Down Expand Up @@ -1197,9 +1197,9 @@ def _get_model_args(self) -> Dict[str, Any]:
args["quantization_config"] = quantization_config
elif self.use_fp16:
if self.device == torch.device("mps"):
args["torch_dtype"] = torch.float16
args["dtype"] = torch.float16
else:
args["torch_dtype"] = torch.bfloat16
args["dtype"] = torch.bfloat16

# We do this, because in some cases, using device:auto will offload some weights to the cpu
# (even though the model might *just* fit to a single gpu), even if there is a gpu available, and this will
Expand Down