Update README.md

README.md

@@ -21,7 +21,7 @@ tags:
 # Quant Infos
 
 - quants done with an importance matrix for improved quantization loss
-- quantized & generated imatrix from the f32 as f16 is inaccurate when conferting from bf16
+- quantized & generated imatrix from the f32 as f16 is inaccurate when converting from bf16
 - K & IQ quants in basically all variants from Q6_K down to IQ1_S
 
 Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [4e96a812b3ce7322a29a3008db2ed73d9087b176](https://github.com/ggerganov/llama.cpp/commit/4e96a812b3ce7322a29a3008db2ed73d9087b176) (master from 2024-04-23) with fixes from [this](https://github.com/ggerganov/llama.cpp/pull/6851) branch cherry-picked