Update README.md
Browse filesSince the ancestry of your model is convoluted, I won't include a list of what was merged, I'll just let them know that you merged a lot.
README.md
CHANGED
@@ -1,10 +1,13 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
3 |
---
|
4 |
-
h2m/mhm-7b-v1.3-DPO-1
|
5 |
|
6 |
-
|
7 |
|
8 |
-
|
|
|
|
|
9 |
|
10 |
Just an experiment.
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
---
|
|
|
6 |
|
7 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/ORVjYrpzyfKfP4ByOQnpQ.jpeg)
|
8 |
|
9 |
+
A DPO fine tuned [mhm-7b-v1.3](https://huggingface.co/h2m/mhm-7b-v1.3) on [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
|
10 |
+
|
11 |
+
Based upon mistral. Created using [dare_ties](https://github.com/cg123/mergekit) and models from openllm leaderboard. Over 3 merges involving 7 different models, this was the result.
|
12 |
|
13 |
Just an experiment.
|