Update README.md

README.md

@@ -35,7 +35,7 @@ model-index:
   results: []
 ---
 
-# Hermes 4 — Llama-3.1 70
+# Hermes 4 — Llama-3.1 70B - FP8
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/roT9o5bMYBtQziRMlaSDf.jpeg)
 
@@ -192,9 +192,9 @@ For production serving on multi-GPU nodes, consider tensor parallel inference en
 
 # Quantized / Smaller Variants
 
-Hermes 4 is available as BF16 original weights as well as FP8 variants and GGUF variants by LM Studio.
+Hermes 4 is available as BF16 original weights as well as BF16 as well as FP8 variants and GGUF variants by LM Studio.
 
-FP8: https://huggingface.co/NousResearch/Hermes-4-70B-FP8
+BF16: https://huggingface.co/NousResearch/Hermes-4-70B
 
 GGUF: Coming soon courtesy of LM Studio team!