CausalLM
/

14B-DPO-alpha

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions

JosephusCheung commited on Dec 2, 2023

Commit

938ac99

·

1 Parent(s): 254116c

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -46,10 +46,10 @@ For details, please refer to the version without DPO training: [CausalLM/14B](ht
 | **CausalLM/14B-DPO-α**    | **7.618868** |
 | **CausalLM/7B-DPO-α**     | **7.038125** |
-Dec 2, 2023
-Rank **#2** non-base model, of its size on 🤗 Open LLM Leaderboard, outperforms ALL ~13B chat models including microsoft/Orca-2-13b.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/63468a143ea42ee2cb49ddd1/Df5BcU3Pxzt2oKjuzArvk.png)
 It should be noted that this is not a version that continues training on CausalLM/14B & 7B, but rather an optimized version that has undergone DPO training concurrently on a previous training branch, and some detailed parameters may have changed. You will still need to download the full model.

 | **CausalLM/14B-DPO-α**    | **7.618868** |
 | **CausalLM/7B-DPO-α**     | **7.038125** |
+Dec 3, 2023
+Rank **#1** non-base model, of its size on 🤗 Open LLM Leaderboard, outperforms **ALL** ~13B chat models.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63468a143ea42ee2cb49ddd1/8nV0yOTteP208bjbCv5MC.png)
 It should be noted that this is not a version that continues training on CausalLM/14B & 7B, but rather an optimized version that has undergone DPO training concurrently on a previous training branch, and some detailed parameters may have changed. You will still need to download the full model.