Update README.md
Browse files
README.md
CHANGED
@@ -4,34 +4,14 @@ base_model:
|
|
4 |
- v000000/2x8B_DPO_TRAIN
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
-
- mergekit
|
8 |
- merge
|
9 |
-
|
|
|
|
|
10 |
---
|
11 |
-
# merge
|
12 |
-
|
13 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
-
|
15 |
-
## Merge Details
|
16 |
-
### Merge Method
|
17 |
-
|
18 |
-
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
19 |
-
|
20 |
-
### Models Merged
|
21 |
-
|
22 |
-
The following models were included in the merge:
|
23 |
-
* [v000000/L3.1-Celestial-Stone-2x8B](https://huggingface.co/v000000/L3.1-Celestial-Stone-2x8B) + [v000000/2x8B_DPO_TRAIN](https://huggingface.co/v000000/2x8B_DPO_TRAIN)
|
24 |
-
|
25 |
-
### Configuration
|
26 |
|
27 |
-
|
28 |
|
29 |
-
|
30 |
-
models:
|
31 |
-
- model: v000000/L3.1-Celestial-Stone-2x8B+v000000/2x8B_DPO_TRAIN
|
32 |
-
parameters:
|
33 |
-
weight: 1.0
|
34 |
-
merge_method: linear
|
35 |
-
dtype: bfloat16
|
36 |
|
37 |
-
|
|
|
4 |
- v000000/2x8B_DPO_TRAIN
|
5 |
library_name: transformers
|
6 |
tags:
|
|
|
7 |
- merge
|
8 |
+
- llama
|
9 |
+
- mixtral
|
10 |
+
- dpo
|
11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
+
# Llama-3.1-Celestial-Stone-2x8B-DPO
|
14 |
|
15 |
+
Direct Preference Optimization - DPO
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
+
[v000000/L3.1-Celestial-Stone-2x8B](https://huggingface.co/v000000/L3.1-Celestial-Stone-2x8B) Finetuned on Nvidia A100, 0.5 Epoch of [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1)
|