Update README.md

README.md

@@ -23,9 +23,9 @@ Training data was assembled across several domains:
 | Genetics & longevity | OpenGenes (expression directionality), SynergyAge (lifespan), CellAge (senescence), anti-aging target classification |
 | Reasoning corpus | Prediction tasks augmented with frontier-model chain-of-thought traces |
 
-Approximate scale across all domains: ≈10⁶ training prompts at the order of several billion tokens total. LFM2-1.2B-Longevity was trained using full-parameter supervised fine-tuning on the longevity training corpus. Exact data composition, prompt and token counts, and training recipe details are reported in the accompanying manuscript.
+Approximate scale across all domains: ≈10⁶ training prompts on the order of several billion tokens total. LFM2-1.2B-Longevity was trained using full-parameter supervised fine-tuning on the longevity training corpus. Exact data composition, prompt and token counts, and training recipe details are reported in the accompanying manuscript.
 
-## Example usage with Transformers (compatible with transformers>=5.1.0)
+## Example usage with Transformers (compatible with `transformers>=5.1.0`)
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -76,6 +76,6 @@ The fine-tuned model is released under LFM Open License v1.0. The underlying bas
   title  = {An Open Benchmark and Language Models for AI in Aging Biology},
   author = {Insilico Medicine and Liquid AI},
   year   = {2026},
-  howpublished = {\url{https://huggingface.co/LiquidAI/LFM2-1.2-Longevity}}
+  howpublished = {\url{https://huggingface.co/LiquidAI/LFM2-1.2B-Longevity}}
 }
 ```