Update strings.py

strings.py

@@ -1,7 +1,7 @@
 TITLE = "Alpaca-LoRA Playground"
 
 ABSTRACT = """
-Thanks to [tolen](https://github.com/tloen/alpaca-lora), this application runs Alpaca-LoRA which is instruction fine-tuned version of [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/). This demo currently runs 30B version on a 3*A6000 instance at [Jarvislabs.ai](https://jarvislabs.ai/).
+Thanks to [tolen](https://github.com/tloen/alpaca-lora), this application runs Alpaca-LoRA which is instruction fine-tuned version of [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/). This demo currently runs 8Bit 13B version on a A10 instance.
 
 NOTE: too long input (context, instruction) will not be allowed. Please keep them < 150
 """
@@ -11,7 +11,6 @@ This demo application runs the open source project, [Alpaca-LoRA-Serve](https://
 
 Alpaca-LoRA is built on the same concept as Standford Alpaca project, but it lets us train and inference on a smaller GPUs such as RTX4090 for 7B version. Also, we could build very small size of checkpoints on top of base models thanks to [🤗 transformers](https://huggingface.co/docs/transformers/index), [🤗 peft](https://github.com/huggingface/peft), and [bitsandbytes](https://github.com/TimDettmers/bitsandbytes/tree/main) libraries.
 
-We are thankful to the [Jarvislabs.ai](https://jarvislabs.ai/) who generously provided free GPU instances.
 """
 
 DEFAULT_EXAMPLES = {