# UserWarning: You are using a decoder-only model with padding_side='right'. This may produce incorrect results. Consider setting `tokenizer.padding_side = 'left'`.

- **ID:** `huggingface/transformers-tokenizer-padding-side-mismatch`
- **Domain:** huggingface
- **Category:** config_error
- **Verification:** ai_generated
- **Fix Rate:** 95%

## Root Cause

Decoder-only models (e.g., GPT, LLaMA) expect padding on the left side for batched generation; using right padding causes the model to attend to padding tokens at the end of the sequence.

## Version Compatibility

| Version | Status | Introduced | Deprecated |
|---------|--------|------------|------------|
| transformers>=4.30.0 | active | — | — |
| torch>=1.12.0 | active | — | — |

## Workarounds

1. **Set padding_side before tokenizing: `tokenizer.padding_side = 'left'` then tokenize the batch again. Example: `tokenizer.padding_side = 'left'; inputs = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')`** (95% success)
   ```
   Set padding_side before tokenizing: `tokenizer.padding_side = 'left'` then tokenize the batch again. Example: `tokenizer.padding_side = 'left'; inputs = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')`
   ```
2. **For generation, use a pipeline with `tokenizer.padding_side = 'left'` and set `pad_token_id=tokenizer.eos_token_id` if no pad token is defined.** (90% success)
   ```
   For generation, use a pipeline with `tokenizer.padding_side = 'left'` and set `pad_token_id=tokenizer.eos_token_id` if no pad token is defined.
   ```
3. **If using Trainer, set `tokenizer.padding_side = 'left'` in the data collator or before creating the dataset to ensure all batches are left-padded.** (85% success)
   ```
   If using Trainer, set `tokenizer.padding_side = 'left'` in the data collator or before creating the dataset to ensure all batches are left-padded.
   ```

## Dead Ends

- **** — The model will generate incorrect tokens because it attends to padding tokens at the end, especially for left-to-right generation tasks like text completion. (80% fail)
- **** — The tokenizer's padding_side only affects future calls to tokenizer(); if you already tokenized the input, the padding direction is already set and won't change. (60% fail)
- **** — This only sets the pad token ID; it does not change the padding direction, so the warning and incorrect behavior persist. (50% fail)