Update README.md
Browse files
README.md
CHANGED
|
@@ -125,6 +125,14 @@ model-index:
|
|
| 125 |
|
| 126 |
Galactic-Qwen-14B-Exp2 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. This model is optimized for general-purpose reasoning and answering, excelling in contextual understanding, logical deduction, and multi-step problem-solving. It has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets to improve comprehension, structured responses, and conversational intelligence.
|
| 127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
## **Key Improvements**
|
| 129 |
1. **Enhanced General Knowledge**: The model provides broad knowledge across various domains, improving capabilities in answering questions accurately and generating coherent responses.
|
| 130 |
2. **Improved Instruction Following**: Significant advancements in understanding and following complex instructions, generating structured responses, and maintaining coherence over extended interactions.
|
|
|
|
| 125 |
|
| 126 |
Galactic-Qwen-14B-Exp2 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-parameter models. This model is optimized for general-purpose reasoning and answering, excelling in contextual understanding, logical deduction, and multi-step problem-solving. It has been fine-tuned using a long chain-of-thought reasoning model and specialized datasets to improve comprehension, structured responses, and conversational intelligence.
|
| 127 |
|
| 128 |
+
<details>
|
| 129 |
+
<summary>BBH (3-Shot) Text Generation Benchmark</summary>
|
| 130 |
+
|
| 131 |
+
- [View Leaderboard on Papers with Code](https://paperswithcode.com/sota/text-generation-on-bbh-3-shot)
|
| 132 |
+
|
| 133 |
+
</details>
|
| 134 |
+
|
| 135 |
+
|
| 136 |
## **Key Improvements**
|
| 137 |
1. **Enhanced General Knowledge**: The model provides broad knowledge across various domains, improving capabilities in answering questions accurately and generating coherent responses.
|
| 138 |
2. **Improved Instruction Following**: Significant advancements in understanding and following complex instructions, generating structured responses, and maintaining coherence over extended interactions.
|