abideen
/

Heimer-ipo-TinyLlama-1.1B

Text Generation

TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

abideen/Heimer-dpo-TinyLlama-1.1B

abideen/Heimer-kto-TinyLlama-1.1B

Intel/orca_dpo_pairs

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

abideen commited on Jan 14

Commit

2989049

•

1 Parent(s): a082853

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ Check out the experiment details in this [report](https://api.wandb.ai/links/zai
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/HLhrSUFD1-e6f31F3WGK2.png)
-# 🧩 DPO adaptation hyperparameters
 ## LoRA:

 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/HLhrSUFD1-e6f31F3WGK2.png)
+# 🧩 IPO adaptation hyperparameters
 ## LoRA: