Update README.md

README.md

@@ -14,12 +14,12 @@ widget:
 # Open-Assistant StableLM-7B SFT-7 Model
 
 
-This is the 4th iteration English supervised-fine-tuning (SFT) model of 
+This is the 7th iteration English supervised-fine-tuning (SFT) model of 
 the [Open-Assistant](https://github.com/LAION-AI/Open-Assistant) project. 
-It is based on a Pythia 12B that was fine-tuned on human demonstrations 
+It is based on a StableLM 7B that was fine-tuned on human demonstrations 
 of assistant conversations collected through the 
 [https://open-assistant.io/](https://open-assistant.io/) human feedback web 
-app before March 25, 2023. 
+app before April 12, 2023. 
 
 ## Model Details
 
@@ -51,7 +51,7 @@ start generating the assistant reply.
 - base model: [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b)
 - checkpoint: 3 epochs (12000 steps)
 
-command: `deepspeed trainer_sft.py --configs defaults reference-data reference-pythia-12b --cache_dir /home/ubuntu/data_cache --output_dir .saved/oasst-sft-3-pythia-12b-reference_2kpre --num_train_epochs 8 --residual_dropout 0.2 --deepspeed --use_flash_attention true --model_name andreaskoepf/pythia-12b-pre-2000`
+command: `deepspeed trainer_sft.py --configs defaults stablelm-7b oasst-mix --cache_dir /home/ubuntu/data_cache --output_dir .saved/stable-lm-7b-1 --num_train_epochs 4 --deepspeed`
 
 data:
 ```