Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ datasets: KingNish/reasoning-base-20k
|
|
| 4 |
Base Model: kz919/QwQ-0.5B-Distilled-SFT
|
| 5 |
---
|
| 6 |
Fine-tuned kz919/QwQ-0.5B-Distilled-SFT upon KingNish/reasoning-base-20k
|
| 7 |
-
|
| 8 |
Original Model Card Follows:
|
| 9 |
---
|
| 10 |
license: apache-2.0
|
|
@@ -194,20 +194,6 @@ print(response)
|
|
| 194 |
- This model could still be under trained, merely a proof of concept. Don't yell at me if it's outputing nonesense.
|
| 195 |
---
|
| 196 |
|
| 197 |
-
## Citation:
|
| 198 |
-
|
| 199 |
-
If you use this model in your research or applications, please cite it as:
|
| 200 |
-
|
| 201 |
-
```bibtex
|
| 202 |
-
@model{qwq_0.5B_distilled,
|
| 203 |
-
author = {Kaizhao Liang},
|
| 204 |
-
title = {Mini-QwQ: A Reasoning Model for Edge Devices},
|
| 205 |
-
year = {2024},
|
| 206 |
-
publisher = {Hugging Face},
|
| 207 |
-
version = {1.0}
|
| 208 |
-
}
|
| 209 |
-
```
|
| 210 |
-
|
| 211 |
---
|
| 212 |
|
| 213 |
This model is an example of how efficient fine-tuning and distillation methods can deliver robust conversational AI capabilities in a smaller, more manageable footprint.
|
|
|
|
| 4 |
Base Model: kz919/QwQ-0.5B-Distilled-SFT
|
| 5 |
---
|
| 6 |
Fine-tuned kz919/QwQ-0.5B-Distilled-SFT upon KingNish/reasoning-base-20k
|
| 7 |
+
---
|
| 8 |
Original Model Card Follows:
|
| 9 |
---
|
| 10 |
license: apache-2.0
|
|
|
|
| 194 |
- This model could still be under trained, merely a proof of concept. Don't yell at me if it's outputing nonesense.
|
| 195 |
---
|
| 196 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 197 |
---
|
| 198 |
|
| 199 |
This model is an example of how efficient fine-tuning and distillation methods can deliver robust conversational AI capabilities in a smaller, more manageable footprint.
|