Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,9 @@ datasets:
|
|
| 27 |
|
| 28 |
Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
|
| 29 |
|
| 30 |
-
Fine-tuning on A100 in 4-bit with unsloth using SIMPO and
|
|
|
|
|
|
|
| 31 |
|
| 32 |
### Eval results
|
| 33 |
|
|
|
|
| 27 |
|
| 28 |
Improved quality on hard tasks by 25 percent relative to the base model Qwen2.5-32B-Instruct. Improved multilingual support.
|
| 29 |
|
| 30 |
+
Fine-tuning on A100 in 4-bit with unsloth using SIMPO and custom dataset
|
| 31 |
+
|
| 32 |
+
LoRA adapter: [radm/Qwen2.5-32B-simpo-LoRA](https://huggingface.co/radm/Qwen2.5-32B-simpo-LoRA)
|
| 33 |
|
| 34 |
### Eval results
|
| 35 |
|