Update README.md

README.md

@@ -114,19 +114,35 @@ model-index:
       url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/NEBULA-23B-v1.0
       name: Open LLM Leaderboard
 ---
-### TeeZee/NEBULA-23B-v1.0 ###
+# NEBULA-23.8B-v1.0
 
 ![image/png](https://huggingface.co/TeeZee/NEBULA-23B-v1.0/resolve/main/NEBULA-23B-v1.0.jpg)
 
 - 108 layers,DUS procedure, mistral(32)->SOLAR(48)->GALAXY(72)->NEBULA(108)
+- 23.8B parameters
 - model created as a extension of depth upscaling procedure used for SOLAR by upstage
 
-### Results
+## Results
 - model can and will produce NSFW content
-- for evaluation of RP and ERP more tests are needed
+- GSM8k evaluation seems to be often broken, HellaSwag, Winograde and TQA show that its a smart model
+- RP and ERP work suprizingly good and I didn't encounter any GPTismsm yet
+- lower memory footprint than 20B and 23B models
+- follows character card very well
+- NSFW output feels fresh comparing to existing models
 
-### Prompt template
+## Finetuning for RP
+- SFT using MinervaAI/Aesir-Preview dataset, 10 epochs
+- DPO using athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW dataset, 1 epoch
+- SFT using 1xAda6000, DPO 1x3090, around 24h for each
+- jupyter notebooks or mergekit configs for anyone wanting to reproduce/reuse scripts - just drop me a message
+
+## Prompt template
 - Alpaca
+- chat template is embedded in tokenizer config, should load automatically
+  
+All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
+<a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
+
 # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TeeZee__NEBULA-23B-v1.0)