iq2_tn: TriLM specific 2.0625 bpw quantization

Quantize/dequantize/scale dot product.

I get 46 t/s for the TriLM-3.9B with any SIMD!
Finally a compiler doing a decent job auto-vectorizing the
scalar implementation.

include/llama.h

@@ -174,6 +174,7 @@ extern "C" {
         LLAMA_FTYPE_MOSTLY_IQ3_K         = 39, // except 1d tensors
         LLAMA_FTYPE_MOSTLY_IQ4_K         = 40, // except 1d tensors
         LLAMA_FTYPE_MOSTLY_IQ5_K         = 41, // except 1d tensors
+        LLAMA_FTYPE_MOSTLY_IQ2_TN        = 42, // except 1d tensors
 
         LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
     };