huggingface/transformers · error · ValueError
Need to specify either input_ids or inputs_embeds.
Error message
Need to specify either input_ids or inputs_embeds.
What it means
Error "Need to specify either input_ids or inputs_embeds." thrown in huggingface/transformers.
Source
Thrown at src/transformers/integrations/executorch.py:299
cache_position=cache_position
)
```
Export with inputs_embeds:
```python
# Prepare embeddings
inputs_embeds = torch.randn(1, 3, 768, device=model.device) # batch_size=1, seq_len=3, hidden_size=768
cache_position = torch.arange(inputs_embeds.shape[1], dtype=torch.long, device=model.device)
# Export
exported = exportable_module.export(
inputs_embeds=inputs_embeds,
cache_position=cache_position
)
```
"""
if not (input_ids is None) ^ (inputs_embeds is None):
raise ValueError("Need to specify either input_ids or inputs_embeds.")
if hasattr(self.model, "base_model_prefix"):
base = getattr(self.model, self.model.base_model_prefix, self.model)
model_device = base.device
elif hasattr(self.model, "model"):
model_device = self.model.model.device
else:
model_device = "cpu"
logging.warning(
"TorchExportableModuleForDecoderOnlyLM.export Can't infer device from the model. Set to CPU by default."
)
if input_ids is not None:
input_kwargs = {
"input_ids": input_ids,
"cache_position": cache_position
if cache_position is not None
else torch.arange(input_ids.shape[-1], dtype=torch.long, device=model_device),View on GitHub (pinned to a597f97485)
Solutions
- Pass either `input_ids` or `inputs_embeds` to the call.
When it happens
Trigger: Raised in ExecuTorch model wrapper when neither input_ids nor inputs_embeds is provided.
Common situations: Calling the exported ExecuTorch module without any token input.
AI-assisted analysis of huggingface/transformers@a597f97485 (2026-08-14).
Data as JSON: /api/errors/d799008787b8fbd8.
Report an issue: GitHub.