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

HTTP/cURL API

Input fields

`prompt`string

`max_length`integer

`do_sample`boolean

`top_k`integer

`num_return_sequences`integer

Input Schema

Output Schema

tiiuae/falcon-7b

HTTP/cURL API

Input fields

promptstring

max_lengthinteger

do_sampleboolean

top_kinteger

num_return_sequencesinteger