Falcon-7B is a 7B parameters causal decoder-only model built by TII and trained on 1,500B tokens of RefinedWeb enhanced with curated corpora. It is made available under the Apache 2.0 license.

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

```bash
curl -X POST \
    -d '{"input": {"prompt": "..."}}'  \
    -H 'Content-Type: application/json'  \
    -H "Authorization: bearer $(deepctl auth token)"  \
    'https://api.deepinfra.com/v1/inference/$MODEL'
```

The inpu/output is compatible with the cog interface.


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

```bash
deepctl infer \
    -m '$MODEL'  \
    -i prompt=...  \
    -i max_length=...  \
    -i do_sample=...
```


tiiuae/falcon-7b

Input

Output