Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,11 @@ pipeline_tag: question-answering
|
|
| 12 |
|
| 13 |
# Model Card for Model ID
|
| 14 |
|
| 15 |
-
This model is trained on **unixyhuang/SmartHome-Device-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |
|
|
|
|
| 12 |
|
| 13 |
# Model Card for Model ID
|
| 14 |
|
| 15 |
+
This model is trained on **unixyhuang/SmartHome-Device-QA** dataset for smart home assistant usage.
|
| 16 |
+
|
| 17 |
+
The base model is llama-3-8B.
|
| 18 |
+
|
| 19 |
+
The fine-tuning method is QLoRA.
|
| 20 |
|
| 21 |
|
| 22 |
|