AINovice2005
commited on
Commit
•
ae63950
1
Parent(s):
d2a3b14
Update README.md
Browse files
README.md
CHANGED
@@ -12,8 +12,6 @@ tags:
|
|
12 |
|
13 |
---
|
14 |
|
15 |
-
<h1 style="font-size: 2em;">ElEmperador </h1>
|
16 |
-
|
17 |
|
18 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e8ea3892d9db9a93580fe3/gkDcpIxRCjBlmknN_jzWN.png)
|
19 |
|
@@ -21,7 +19,7 @@ tags:
|
|
21 |
|
22 |
ElEmperador is an ORPO-based finetinue derived from the Mistral-7B-v0.1 base model.
|
23 |
|
24 |
-
The [argilla/ultrafeedback-binarized-preferences-cleaned dataset
|
25 |
|
26 |
# Evals:
|
27 |
BLEU:0.209
|
|
|
12 |
|
13 |
---
|
14 |
|
|
|
|
|
15 |
|
16 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e8ea3892d9db9a93580fe3/gkDcpIxRCjBlmknN_jzWN.png)
|
17 |
|
|
|
19 |
|
20 |
ElEmperador is an ORPO-based finetinue derived from the Mistral-7B-v0.1 base model.
|
21 |
|
22 |
+
The [https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned] dataset was used for training, albeit a small portion was used due to GPU constraints.
|
23 |
|
24 |
# Evals:
|
25 |
BLEU:0.209
|