Update README.md (#1)

- Update README.md (231f437e9f081c94ce0ef3ea13659fed02f89c37)

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-pipeline_tag: text-to-text
+pipeline_tag: text-generation
 base_model: inclusionAI/Ling-3.1-flash
 base_model_relation: quantized
 quantized_by: turboderp
@@ -14,4 +14,6 @@ EXL3 quants of [Ling-3.1-flash](https://huggingface.co/inclusionAI/Ling-3.1-flas
 
 # Plain quants:
 
-[2.10 bits per weight](https://huggingface.co/turboderp/Ling-3.1-flash-exl3/tree/2.10bpw)    
+[2.10 bits per weight](https://huggingface.co/turboderp/Ling-3.1-flash-exl3/tree/2.10bpw)    
+
+*(benchmark, more bitrates and self-calibrated quants to follow)*