Restore adapter metadata
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# BehaviorTune QLoRA Adapter
|
| 2 |
|
| 3 |
QLoRA adapter for `Qwen/Qwen3-4B-Instruct-2507`, trained on the 240-row BehaviorTune training split and evaluated with matched BASE / SYSTEM / CONTEXT / QLoRA conditions.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
license: other
|
| 6 |
+
datasets:
|
| 7 |
+
- aamish-ahmad/behaviortune-v1-1-r1
|
| 8 |
+
tags:
|
| 9 |
+
- lora
|
| 10 |
+
- qlora
|
| 11 |
+
- behavioral-evaluation
|
| 12 |
+
- llm
|
| 13 |
+
- post-training
|
| 14 |
+
- model-evaluation
|
| 15 |
+
- qwen
|
| 16 |
+
- synthetic-data
|
| 17 |
+
---
|
| 18 |
# BehaviorTune QLoRA Adapter
|
| 19 |
|
| 20 |
QLoRA adapter for `Qwen/Qwen3-4B-Instruct-2507`, trained on the 240-row BehaviorTune training split and evaluated with matched BASE / SYSTEM / CONTEXT / QLoRA conditions.
|