Hugging Face's logo

abideen
/
Heimer-ipo-TinyLlama-1.1B

Text Generation
Transformers
Safetensors
English
llama
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 Community
abideen commited on
Commit
2989049
·
verified ·
1 Parent(s): a082853

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -25,7 +25,7 @@ Check out the experiment details in this [report](https://api.wandb.ai/links/zai
25
 
26
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/HLhrSUFD1-e6f31F3WGK2.png)
27
 
28
- # 🧩 DPO adaptation hyperparameters
29
 
30
  ## LoRA:
31
 
 
25
 
26
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/HLhrSUFD1-e6f31F3WGK2.png)
27
 
28
+ # 🧩 IPO adaptation hyperparameters
29
 
30
  ## LoRA:
31