Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ FireFunction is a state-of-the-art function calling model with a commercially vi
|
|
16 |
|
17 |
π¨ Blazing fast speed. Inference speeds are roughly 4x that of GPT-4 when using FireFunction hosted on the Fireworks platform
|
18 |
|
19 |
-
π Support for "any"
|
20 |
|
21 |
β
The model is also API compatible with [OpenAI function calling](https://platform.openai.com/docs/guides/function-calling).
|
22 |
```sh
|
|
|
16 |
|
17 |
π¨ Blazing fast speed. Inference speeds are roughly 4x that of GPT-4 when using FireFunction hosted on the Fireworks platform
|
18 |
|
19 |
+
π Support for "any" parameter in tool_choice. Firefunction is the only model that we're aware that supports an option for the model to always choose a function - particularly helpful for routing use cases
|
20 |
|
21 |
β
The model is also API compatible with [OpenAI function calling](https://platform.openai.com/docs/guides/function-calling).
|
22 |
```sh
|