Commit
·
575f18e
1
Parent(s):
c2344ec
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,5 +2,7 @@
|
|
| 2 |
license: llama2
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
-
|
|
|
|
| 2 |
license: llama2
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
datasets:
|
| 6 |
+
- Locutusque/InstructMix
|
| 7 |
---
|
| 8 |
+
meta-llama/Llama-2-13b-hf has been fully fine-tuned on Locutusque/InstructMix. The current weights are the outcome of a test run, having been trained on only 4,000 examples. More epochs are planned for this model. Despite the small training session, the model still achieved a good average loss of about 0.9.
|