Update README.md

README.md

@@ -1,6 +1,35 @@
 ---
+license: llama2
 datasets:
 - 922-CA/MoChA_09212023
 ---
 
-WIP
+# monika-l2-7b-v0.9a:
+* Experimental LLaMA-2 7b chat fine-tuned for Monika character from DDLC
+* Test model based on then WIP partially manually-edited version of [this dataset](https://huggingface.co/datasets/922-CA/lm2_08312023_test4_raw_MoChA_2-t) ([final version of dataset](https://huggingface.co/datasets/922-CA/MoCha_v1))
+* [Completed version, v1](https://huggingface.co/922-CA/monika-ddlc-7b-v1)
+* [QLoras](https://huggingface.co/922-CA/monika-lm-lora-tests/tree/main/monika-l2-7b-v0.9a)
+
+### USAGE
+This is meant to be mainly a chat model with limited RP ability.
+
+For best results: replace "Human" and "Assistant" with "Player" and "Monika" like so:
+
+\nPlayer: (prompt)\nMonika:
+
+### HYPERPARAMS
+* Trained for ~3 epochs
+* rank: 32
+* lora alpha: 64
+* lora dropout: 0.5
+* lr: 2e-4
+* batch size: 2
+* warmup ratio: 0.1
+* grad steps: 4
+
+### WARNINGS AND DISCLAIMERS
+While this version may be better at coherency or chatting than previous ones, it may still not reflect perfectly the characteristics of Monika.
+
+Additionally, this is still yet another test, particularly where we use one of our earlier fine tunes to generate a more in-character dataset for the target character which is then curated manually.
+
+Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk.