Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ language:
|
|
| 18 |
|
| 19 |
| **Field** | **Value** |
|
| 20 |
|-----------------------|--------------------------------------------|
|
| 21 |
-
| **Developed by** | **
|
| 22 |
| **License** | Apache 2.0 |
|
| 23 |
| **Finetuned from** | `unsloth/Qwen2.5-3B-Instruct` |
|
| 24 |
| **Training Framework**| [Unsloth](https://github.com/unslothai/unsloth) × Hugging Face TRL |
|
|
@@ -204,7 +204,7 @@ Stay tuned—numbers landing faster than you can say “schema validation.”
|
|
| 204 |
```bibtex
|
| 205 |
@misc{bhaviktheslider_2025_unsloth_qwen2.5_3b_grpo,
|
| 206 |
title = {An Unsloth-accelerated GRPO-trained Qwen 2.5-3B for JSON structuring},
|
| 207 |
-
author = {
|
| 208 |
year = {2025},
|
| 209 |
howpublished = {\url{https://huggingface.co/MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Lora}}
|
| 210 |
}
|
|
|
|
| 18 |
|
| 19 |
| **Field** | **Value** |
|
| 20 |
|-----------------------|--------------------------------------------|
|
| 21 |
+
| **Developed by** | **MasterControlAIML** |
|
| 22 |
| **License** | Apache 2.0 |
|
| 23 |
| **Finetuned from** | `unsloth/Qwen2.5-3B-Instruct` |
|
| 24 |
| **Training Framework**| [Unsloth](https://github.com/unslothai/unsloth) × Hugging Face TRL |
|
|
|
|
| 204 |
```bibtex
|
| 205 |
@misc{bhaviktheslider_2025_unsloth_qwen2.5_3b_grpo,
|
| 206 |
title = {An Unsloth-accelerated GRPO-trained Qwen 2.5-3B for JSON structuring},
|
| 207 |
+
author = {MasterControlAIML},
|
| 208 |
year = {2025},
|
| 209 |
howpublished = {\url{https://huggingface.co/MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Lora}}
|
| 210 |
}
|