alexchen4ai
commited on
Fix some typo
Browse files
README.md
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
base_model: google/gemma-2b
|
4 |
model-index:
|
5 |
- name: Octopus-V2-2B
|
6 |
results: []
|
7 |
tags:
|
8 |
- function calling
|
|
|
9 |
---
|
10 |
# Octopus V2: On-device language model for super agent
|
11 |
<p align="center">
|
@@ -25,7 +26,7 @@ Octopus-V2-2B, an advanced open-source language model with 2 billion parameters,
|
|
25 |
|
26 |
🐙 **Accuracy**: Octopus-V2-2B not only excels in speed but also in accuracy, surpassing the "Llama7B + RAG solution" in function call accuracy by 31%. It achieves a function call accuracy comparable to GPT-4 and RAG + GPT-3.5, with scores ranging between 98% and 100% across benchmark datasets.
|
27 |
|
28 |
-
💪 **Function Calling Capabilities**: Octopus-V2-2B is capable of
|
29 |
|
30 |
## Example Use Cases
|
31 |
<p align="center" width="100%">
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
base_model: google/gemma-2b
|
4 |
model-index:
|
5 |
- name: Octopus-V2-2B
|
6 |
results: []
|
7 |
tags:
|
8 |
- function calling
|
9 |
+
- on-device language model
|
10 |
---
|
11 |
# Octopus V2: On-device language model for super agent
|
12 |
<p align="center">
|
|
|
26 |
|
27 |
🐙 **Accuracy**: Octopus-V2-2B not only excels in speed but also in accuracy, surpassing the "Llama7B + RAG solution" in function call accuracy by 31%. It achieves a function call accuracy comparable to GPT-4 and RAG + GPT-3.5, with scores ranging between 98% and 100% across benchmark datasets.
|
28 |
|
29 |
+
💪 **Function Calling Capabilities**: Octopus-V2-2B is capable of generating individual, nested, and parallel function calls across a variety of complex scenarios.
|
30 |
|
31 |
## Example Use Cases
|
32 |
<p align="center" width="100%">
|