Zack Zhiyuan Li
commited on
Commit
•
d7b8aeb
1
Parent(s):
cead849
update readme
Browse files
README.md
CHANGED
|
@@ -30,10 +30,13 @@ Octopus-V1, a series of advanced open-source language models with parameters ran
|
|
| 30 |
|
| 31 |
🎯 **Conditional Masking**: A novel conditional masking technique is employed to ensure outputs adhere to the desired formats and reduce errors. This approach not only maintains fast inference speeds but also substantially increases the model's accuracy in generating function calls and parameters.
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
## Example Use Cases
|
| 34 |
-
<p align="center" width="100%">
|
| 35 |
-
<a><img src="tool-usage-compressed.png" alt="ondevice" style="width: 80%; min-width: 300px; display: block; margin: auto;"></a>
|
| 36 |
-
</p>
|
| 37 |
|
| 38 |
You can run the model on a GPU using the following code.
|
| 39 |
```python
|
|
|
|
| 30 |
|
| 31 |
🎯 **Conditional Masking**: A novel conditional masking technique is employed to ensure outputs adhere to the desired formats and reduce errors. This approach not only maintains fast inference speeds but also substantially increases the model's accuracy in generating function calls and parameters.
|
| 32 |
|
| 33 |
+
Here is a full list of fined-tuned models in the Octopus series:
|
| 34 |
+
- [Octopus-v1 Gemma-7B](https://huggingface.co/NexaAIDev/Octopus-v1)
|
| 35 |
+
- [Octopus-v1 llama-7B](https://huggingface.co/NexaAIDev/Octopus-v1-llama-7b)
|
| 36 |
+
- [Octopus-v1 stable-code-3B](https://huggingface.co/NexaAIDev/Octopus-v1-stable-code-3b)
|
| 37 |
+
- [Octopus-v1 Gemma-2B](https://huggingface.co/NexaAIDev/Octopus-v1-gemma-2b)
|
| 38 |
+
|
| 39 |
## Example Use Cases
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
You can run the model on a GPU using the following code.
|
| 42 |
```python
|