Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,9 @@ base_model:
|
|
| 10 |
|
| 11 |
We are thrilled to announce the release of **OLAFv2**, our state-of-the-art Korean language model, now available on Hugging Face! 🎉 Designed to excel in complex reasoning, mathematical problem-solving, and general language understanding, OLAFv2 represents a significant leap forward in NLP capabilities for the Korean language.
|
| 12 |
|
|
|
|
|
|
|
|
|
|
| 13 |
## Key Features of OLAFv2 🌟
|
| 14 |
|
| 15 |
### **Two Model Sizes for Flexibility**
|
|
@@ -25,11 +28,34 @@ One of OLAFv2's standout features is its **Reasoning Mode**, specifically design
|
|
| 25 |
|
| 26 |
This mode can be effectively utilized for **Test-Time Scaling**, enabling the model to harness additional computational resources during inference. This approach enhances output detail and accuracy, achieving performance levels that surpass GPT-4o. 📈
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
### **Long Context Support** 📜
|
| 29 |
With support for up to **32K tokens**, OLAFv2 is perfect for:
|
| 30 |
- Retrieval-Augmented Generation (RAG). 🛠️
|
| 31 |
- Tasks requiring long-context understanding and reasoning. 🧵
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
## Getting Started 🚀
|
| 34 |
OLAFv2 is now available on Hugging Face! You can start using it by accessing our repository:
|
| 35 |
|
|
|
|
| 10 |
|
| 11 |
We are thrilled to announce the release of **OLAFv2**, our state-of-the-art Korean language model, now available on Hugging Face! 🎉 Designed to excel in complex reasoning, mathematical problem-solving, and general language understanding, OLAFv2 represents a significant leap forward in NLP capabilities for the Korean language.
|
| 12 |
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
## Key Features of OLAFv2 🌟
|
| 17 |
|
| 18 |
### **Two Model Sizes for Flexibility**
|
|
|
|
| 28 |
|
| 29 |
This mode can be effectively utilized for **Test-Time Scaling**, enabling the model to harness additional computational resources during inference. This approach enhances output detail and accuracy, achieving performance levels that surpass GPT-4o. 📈
|
| 30 |
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
### **Long Context Support** 📜
|
| 36 |
With support for up to **32K tokens**, OLAFv2 is perfect for:
|
| 37 |
- Retrieval-Augmented Generation (RAG). 🛠️
|
| 38 |
- Tasks requiring long-context understanding and reasoning. 🧵
|
| 39 |
|
| 40 |
+
## Benchmarks and Performance 📊
|
| 41 |
+
|
| 42 |
+
We share evaluation results across three benchmarks, KMMLU, HRM8K and LogicKor.
|
| 43 |
+
|
| 44 |
+
<div style="text-align: center;">
|
| 45 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/650c0029987b1ae4e51fa2d4/rCloMEgq16D8-UuCkM8Pa.png" width="700px" height="450px" title="polyglot_budget" alt="polyglot_budget"/>
|
| 46 |
+
</div>
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
We also share results with inference-time scaling. For more details have a look into our [blog](https://www.onelineai.com/blog/test-time-scaling).
|
| 50 |
+
|
| 51 |
+
<!--   -->
|
| 52 |
+
|
| 53 |
+
<div style="display: flex; justify-content: space-between; align-items: center;">
|
| 54 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/650c0029987b1ae4e51fa2d4/Qa2-91s0nvwIsx0cjRM-W.png" alt="alt-text-1" title="title-1" style="width: 40%;"/>
|
| 55 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/650c0029987b1ae4e51fa2d4/8eATw4sMb-OrgqhRujR0z.png" alt="alt-text-2" title="title-2" style="width: 40%;"/>
|
| 56 |
+
</div>
|
| 57 |
+
|
| 58 |
+
|
| 59 |
## Getting Started 🚀
|
| 60 |
OLAFv2 is now available on Hugging Face! You can start using it by accessing our repository:
|
| 61 |
|