Qin Liu
commited on
Commit
•
c4b266d
1
Parent(s):
acc2564
End of training
Browse files
README.md
CHANGED
|
@@ -1,8 +1,11 @@
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Meta-Llama-3-8B
|
|
|
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
license: llama3
|
| 5 |
tags:
|
|
|
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
|
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# llama3-sudo-sanity
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 1.1030
|
| 22 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Meta-Llama-3-8B
|
| 3 |
+
datasets:
|
| 4 |
+
- HuggingFaceH4/ultrachat_200k
|
| 5 |
library_name: peft
|
| 6 |
license: llama3
|
| 7 |
tags:
|
| 8 |
+
- alignment-handbook
|
| 9 |
- trl
|
| 10 |
- sft
|
| 11 |
- generated_from_trainer
|
|
|
|
| 19 |
|
| 20 |
# llama3-sudo-sanity
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the HuggingFaceH4/ultrachat_200k dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: 1.1030
|
| 25 |
|