Commit ·
c463b0a
1
Parent(s): e5697cb
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,7 @@ base_model: Locutusque/TinyMistral-248M
|
|
| 4 |
license: apache-2.0
|
| 5 |
datasets:
|
| 6 |
- Locutusque/InstructMixCleaned
|
|
|
|
| 7 |
language:
|
| 8 |
- en
|
| 9 |
widget:
|
|
@@ -33,4 +34,4 @@ inference:
|
|
| 33 |
repetition_penalty: 1.176
|
| 34 |
---
|
| 35 |
Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
|
| 36 |
-
It has so far been trained on approximately
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
datasets:
|
| 6 |
- Locutusque/InstructMixCleaned
|
| 7 |
+
- berkeley-nest/Nectar
|
| 8 |
language:
|
| 9 |
- en
|
| 10 |
widget:
|
|
|
|
| 34 |
repetition_penalty: 1.176
|
| 35 |
---
|
| 36 |
Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
|
| 37 |
+
It has so far been trained on approximately 608,000 examples. More epochs are planned for this model.
|