Update README.md

README.md

@@ -1,11 +1,10 @@
 ---
 library_name: transformers
-license: apache-2.0
 base_model: Heralax/etiquette-pretrain
 tags:
 - generated_from_trainer
 model-index:
-- name: us-army-finetune-1
+- name: mannerstral
   results: []
 ---
 
@@ -42,14 +41,14 @@ datasets:
     conversation: chatml
 
 dataset_prepared_path: last_run_prepared
-output_dir: ./us-army-finetune-1
+output_dir: ./manners-finetune-1
 
 sequence_len: 4096
 sample_packing: true
 pad_to_sequence_len: true
 shuffle_merged_datasets: true
 
-wandb_project: mistral-usarmy
+wandb_project: mannerstral
 wandb_entity:
 wandb_watch:
 wandb_run_id:
@@ -96,21 +95,24 @@ special_tokens:
 
 </details><br>
 
-# us-army-finetune-1
+# Mannerstral 7b
 
-This model is a fine-tuned version of [Heralax/etiquette-pretrain](https://huggingface.co/Heralax/etiquette-pretrain) on the None dataset.
+A must-have for shut-in AI nerds everywhere, this LLM is a domain expert on manners and etiquette. Particularly, the manners and etiquette of the previous century, because all I had was Project Gutenberg.
 
-## Model description
+This model is very tightly focused on factual question answer. I find that these models can be a bit subject to leading questions... I'm working on a specific idea for a countermeasure but it will take some time.
 
-More information needed
+## Model Quirks
 
-## Intended uses & limitations
+- ChatML
+- No generalist assistant data included, but it seems capable-ish of it still
+- Data generated with llama 3 70b and llama 3 8b
+- Low temperature recommended, screenshots use 0
+- No special tokens added
+- Subject to leading questions -- if you ask it how to politely welcome a guest in one message, and then how to politely punch someone, it will probably not correct you the second time (as opposed to possibly correcting you if you asked how to punch someone in the first message).
+  - Prompting may be able to ameliorate this.
 
-More information needed
+Examples:
 
-## Training and evaluation data
-
-More information needed
 
 ## Training procedure
 
@@ -133,7 +135,7 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-
+"it is considered a serious breach of etiquette to throw anyone out of a window" I think it came out all right.
 
 ### Framework versions