Update README.md
Browse files
README.md
CHANGED
@@ -208,10 +208,10 @@ Several issues were observed during initial evaluations:
|
|
208 |
Amongst all tested models 'Command r plus' showed highest precision especially noted for its critical analysis capabilities and adherence to structured prompts.
|
209 |
|
210 |
**4.Model Training & Results:**
|
211 |
-
The final model was developed using full
|
212 |
|
213 |
Training specifics included:
|
214 |
-
* Dataset size :
|
215 |
* Epochs : One
|
216 |
* Batch Size : 64
|
217 |
|
|
|
208 |
Amongst all tested models 'Command r plus' showed highest precision especially noted for its critical analysis capabilities and adherence to structured prompts.
|
209 |
|
210 |
**4.Model Training & Results:**
|
211 |
+
The final model was developed using full ORPO finetune technique on VAGOsolutions/SauerkrautLM-1.5b which is based on qwen2 architecture achieving an impressive accuracy rate close approximating that seen with ‘Command r plus’.
|
212 |
|
213 |
Training specifics included:
|
214 |
+
* Dataset size : 500k unique entries
|
215 |
* Epochs : One
|
216 |
* Batch Size : 64
|
217 |
|