Update README.md

README.md

@@ -17,7 +17,7 @@ library_name: sfttrainer
 
 # BitNet 1.58b 2B Fine-tuned on F*
 
-This model is a SFTTrainer fine-tuned version of Microsoft's Phi-2 trained to generate F* code and automated proofs in the F* formal verification language. In their paper [Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming](https://arxiv.org/pdf/2405.01787), Saikat Chakraborty et al. (2024) use Phi-2, among other LLMs, for evaluating their dataset. This LLM is relatively small and can be fine-tuned on consumer-grade GPUs using LoRA. We wanted to see what could be achieved with BitNet.
+This model is a SFTTrainer fine-tuned version of Microsoft's BitNet 1.58b 2B LLM trained to generate F* code and automated proofs in the F* formal verification language.
 
 ## Model Details