Update README.md

README.md

@@ -1,16 +1,11 @@
----
-datasets:
-  - PygmalionAI/PIPPA
-  - ludis/geepeetee4
----
-
 ## GGUF
 
 gguf quants for ludis/tsukasa-13b-qlora-limarp
 
+
 ## Prompting
 
-https://rentry.org/v43eo - reccomended prompts and gen settings
+https://rentry.org/tsukasa13b - reccomended prompts and gen settings
 
 The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
 
@@ -18,13 +13,12 @@ The `<|system|>` prompt can be used to inject out-of-channel information behind
 
 ## Training
 
-base model (llama-2-13b-hf)
-
-tuned on koishi dataset (commit c83d922) for 1 epoch
+base model (mistral-0.1-7b)
 
-then tuned on pippa dataset (commit 6412b0c) for 1 epoch
+[axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training
+on a 4x nvidia a40 gpu cluster.
 
-then tuned on geepeetee4 dataset (commit c83d922) for 1 epoch
+the a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/).
 
-then tuned on limarp (without ponyville, lolicit, and all the fallen subsets. Version 2023-09-14) for 2 epochs
+rank 8 lora tune of mistralai/Mistral-7B-v0.1, first tuned on koishi commit 6e675d1 for one epoch then on limarp (without ponyville, lolicit, all the fallen, and eka's portal subsets) Version 2023-09-30 for 2 epochs in metharme format