Commit
•
5ec86cf
1
Parent(s):
2388e61
Update README.md
Browse files
README.md
CHANGED
@@ -5,33 +5,18 @@ tags:
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- unsloth
|
8 |
-
- generated_from_trainer
|
9 |
base_model: ayoubkirouane/Mistral-SLERP-Merged7B
|
10 |
model-index:
|
11 |
- name: outputs
|
12 |
results: []
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
-
|
16 |
-
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
-
|
19 |
-
|
20 |
-
This model is a fine-tuned version of [ayoubkirouane/Mistral-SLERP-Merged7B](https://huggingface.co/ayoubkirouane/Mistral-SLERP-Merged7B) on the None dataset.
|
21 |
-
|
22 |
-
## Model description
|
23 |
-
|
24 |
-
More information needed
|
25 |
-
|
26 |
-
## Intended uses & limitations
|
27 |
-
|
28 |
-
More information needed
|
29 |
-
|
30 |
-
## Training and evaluation data
|
31 |
-
|
32 |
-
More information needed
|
33 |
-
|
34 |
-
## Training procedure
|
35 |
|
36 |
### Training hyperparameters
|
37 |
|
@@ -48,10 +33,6 @@ The following hyperparameters were used during training:
|
|
48 |
- num_epochs: 1
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
-
### Training results
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
### Framework versions
|
56 |
|
57 |
- PEFT 0.7.1
|
|
|
5 |
- trl
|
6 |
- dpo
|
7 |
- unsloth
|
|
|
8 |
base_model: ayoubkirouane/Mistral-SLERP-Merged7B
|
9 |
model-index:
|
10 |
- name: outputs
|
11 |
results: []
|
12 |
+
datasets:
|
13 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
14 |
+
pipeline_tag: text-generation
|
15 |
---
|
16 |
|
17 |
+
# Mistral-SLERP-Merged7B-DPO
|
|
|
18 |
|
19 |
+
- DPO finetuned version from my [Mistral-SLERP-Merged7B](https://huggingface.co/ayoubkirouane/Mistral-SLERP-Merged7B)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
### Training hyperparameters
|
22 |
|
|
|
33 |
- num_epochs: 1
|
34 |
- mixed_precision_training: Native AMP
|
35 |
|
|
|
|
|
|
|
|
|
36 |
### Framework versions
|
37 |
|
38 |
- PEFT 0.7.1
|