DistilRoBERTa is a distilled version of the RoBERTa-base model, with 6 layers, 768 dimensions, and 12 heads, totaling 82M parameters. It is trained on OpenWebTextCorpus, a reproduction of OpenAI's WebText dataset, and achieves comparable performance to RoBERTa while being twice as fast. The model is designed for masked language modeling and can be fine-tuned for downstream tasks, but it also comes with potential biases and limitations, including significant gender and ethnicity biases in its predictions.

You can use cURL or any other http client to run inferences:

```bash
curl -X POST \
    -d '{"input": "Where is my <mask>?"}'  \
    -H "Authorization: bearer $(deepctl auth token)"  \
    -H 'Content-Type: application/json'  \
    'https://api.deepinfra.com/v1/inference/distilroberta-base'
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "sequence": "where is my father?",
      "score": 0.08898820728063583,
      "token": 2269,
      "token_str": "father"
    },
    {
      "sequence": "where is my mother?",
      "score": 0.07864926755428314,
      "token": 2388,
      "token_str": "mother"
    }
  ],
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


You can use our command-line tool [deepctl](/docs/getting-started) to run
inferences:

```bash
deepctl infer \
    -m 'distilroberta-base'  \
    -i 'input=Where is my <mask>?'
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "sequence": "where is my father?",
      "score": 0.08898820728063583,
      "token": 2269,
      "token_str": "father"
    },
    {
      "sequence": "where is my mother?",
      "score": 0.07864926755428314,
      "token": 2388,
      "token_str": "mother"
    }
  ],
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


text prompt, should include exactly one <mask> token

input

The webhook to call when inference is done, by default you will get the output in the response of your inference request