This paper presents a fine-tuned German Medical BERT model for the medical domain, achieving improved performance on the NTS-ICD-10 text classification task. The model was trained using PyTorch and Hugging Face library on Colab GPU, with standard parameter settings and up to 25 epochs for classification. Evaluation results show significant improvement in micro precision, recall, and F1 score compared to the base German BERT model.

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/smanjil/German-MedBERT'
```

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 'smanjil/German-MedBERT'  \
    -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

webhook

Input

Webhook

FillMaskIn

How good of a match is this, higher is better

Score

The full input sequence with mask filled in

Sequence

Token

Token Str

Item

estimated cost billed for the request in USD

Cost

Runtime Ms

Status

Tokens Generated

Tokens Input

Object containing the status of the inference request

Inference Status

Request Id

A list of top suggestions, ordered by score