Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ language:
|
|
| 18 |
|
| 19 |
## Octopus V4 Release
|
| 20 |
We are excited to announce that Octopus v4 is now available! Octopus-V4-3B, an advanced open-source language model with 3 billion parameters, serves as the master node in Nexa AI's envisioned graph of language models. Tailored specifically for the MMLU benchmark topics, this model efficiently translates user queries into formats that specialized models can effectively process. It excels at directing these queries to the appropriate specialized model, ensuring precise and effective query handling.
|
| 21 |
-
check our papers and
|
| 22 |
- [paper](https://arxiv.org/abs/2404.19296)
|
| 23 |
- [Octopus V4 model page](https://huggingface.co/NexaAIDev/Octopus-v4)
|
| 24 |
- [Octopus V4 quantized model page](https://huggingface.co/NexaAIDev/octopus-v4-gguf)
|
|
@@ -40,10 +40,6 @@ Key Features of Octopus v3:
|
|
| 40 |
|
| 41 |
Check the Octopus V3 demo video for [Android and iOS](https://octopus3.nexa4ai.com/).
|
| 42 |
|
| 43 |
-
<p align="center" width="100%">
|
| 44 |
-
<a><img src="octopus-v3.jpeg" alt="nexa-octopus-v3" style="width: 30%; min-width: 200px; display: block; margin: auto;"></a>
|
| 45 |
-
</p>
|
| 46 |
-
|
| 47 |
|
| 48 |
## Octopus V2 Release
|
| 49 |
After open-sourcing our model, we got many requests to compare our model with [Apple's OpenELM](https://huggingface.co/apple/OpenELM-3B-Instruct) and [Microsoft's Phi-3](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct). Please see [Evaluation section](#evaluation). From our benchmark dataset, Microsoft's Phi-3 achieves accuracy of 45.7% and the average inference latency is 10.2s. While Apple's OpenELM fails to generate function call, please see [this screenshot](https://huggingface.co/NexaAIDev/Octopus-v2/blob/main/OpenELM-benchmark.jpeg). Our model, Octopus V2, achieves 99.5% accuracy and the average inference latency is 0.38s.
|
|
|
|
| 18 |
|
| 19 |
## Octopus V4 Release
|
| 20 |
We are excited to announce that Octopus v4 is now available! Octopus-V4-3B, an advanced open-source language model with 3 billion parameters, serves as the master node in Nexa AI's envisioned graph of language models. Tailored specifically for the MMLU benchmark topics, this model efficiently translates user queries into formats that specialized models can effectively process. It excels at directing these queries to the appropriate specialized model, ensuring precise and effective query handling.
|
| 21 |
+
check our papers and repos:
|
| 22 |
- [paper](https://arxiv.org/abs/2404.19296)
|
| 23 |
- [Octopus V4 model page](https://huggingface.co/NexaAIDev/Octopus-v4)
|
| 24 |
- [Octopus V4 quantized model page](https://huggingface.co/NexaAIDev/octopus-v4-gguf)
|
|
|
|
| 40 |
|
| 41 |
Check the Octopus V3 demo video for [Android and iOS](https://octopus3.nexa4ai.com/).
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
## Octopus V2 Release
|
| 45 |
After open-sourcing our model, we got many requests to compare our model with [Apple's OpenELM](https://huggingface.co/apple/OpenELM-3B-Instruct) and [Microsoft's Phi-3](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct). Please see [Evaluation section](#evaluation). From our benchmark dataset, Microsoft's Phi-3 achieves accuracy of 45.7% and the average inference latency is 10.2s. While Apple's OpenELM fails to generate function call, please see [this screenshot](https://huggingface.co/NexaAIDev/Octopus-v2/blob/main/OpenELM-benchmark.jpeg). Our model, Octopus V2, achieves 99.5% accuracy and the average inference latency is 0.38s.
|