Update README.md

README.md

@@ -135,3 +135,20 @@ Noting the last remark, while the lora works it was really just for getting more
 * From [Kimiko-LLaMA-2-7b](https://huggingface.co/johnwick123forevr/Llama2-chat-kimiko-Sharded-2gb)
 * 3 epochs
 * Lora of [l2-7b-monika-ddlc-v0.3m-Kv2-c](https://huggingface.co/922-CA/l2-7b-monika-ddlc-v0.3m-Kv2-c)
+
+# monika-ddlc-mistral-v0.1-7b-test qloras (~10/03/2023)
+* Fine-tuned on then WIP partially manually-edited version of [this dataset](https://huggingface.co/datasets/922-CA/lm2_08312023_test4_raw_MoChA_2-t)
+* From [Mistral-7b-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+* Various epochs (2, 3, 10)
+* All had repetition issues, hence why LLaMA-2-7b chat was reused for later versions; may retest again
+
+# monika-ddlc-l2-v0.9 qloras (~10/07/2023)
+* Fine-tuned on then WIP partially manually-edited version of [this dataset](https://huggingface.co/datasets/922-CA/lm2_08312023_test4_raw_MoChA_2-t)
+* From chat LLaMA-2s (7b, 13b)
+* 3 epochs
+
+# monika-ddlc-v1 qloras (~10/03/2023)
+* Fine-tuned on [MoCha v1](https://huggingface.co/datasets/922-CA/MoCha_v1)
+* From chat LLaMA-2-7b
+* 3 epochs
+* Lora of [monika-ddlc-7b-v1](https://huggingface.co/922-CA/monika-ddlc-7b-v1)