Add two new quantization types in quantize.cpp

Author: Srihari-mcw

examples/quantize/quantize.cpp

@@ -17,6 +17,7 @@ struct quant_option {
 
 static const std::vector<struct quant_option> QUANT_OPTIONS = {
     { "Q4_0",   LLAMA_FTYPE_MOSTLY_Q4_0,   " 4.34G, +0.4685 ppl @ Llama-3-8B",  },
+    { "Q4_0_B16", LLAMA_FTYPE_MOSTLY_Q4_0_B16, " 3.56G, 5.9624 +/- 0.03348 ppl @ LLaMA-v2-7B", },
     { "Q4_1",   LLAMA_FTYPE_MOSTLY_Q4_1,   " 4.78G, +0.4511 ppl @ Llama-3-8B",  },
     { "Q5_0",   LLAMA_FTYPE_MOSTLY_Q5_0,   " 5.21G, +0.1316 ppl @ Llama-3-8B",  },
     { "Q5_1",   LLAMA_FTYPE_MOSTLY_Q5_1,   " 5.65G, +0.1062 ppl @ Llama-3-8B",  },
@@ -46,6 +47,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
     { "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 5.33G, +0.0569 ppl @ Llama-3-8B",  },
     { "Q6_K",   LLAMA_FTYPE_MOSTLY_Q6_K,   " 6.14G, +0.0217 ppl @ Llama-3-8B",  },
     { "Q8_0",   LLAMA_FTYPE_MOSTLY_Q8_0,   " 7.96G, +0.0026 ppl @ Llama-3-8B",  },
+    { "Q8_0_B16", LLAMA_FTYPE_MOSTLY_Q8_0_B16, " 6.70G, 5.8011 +/- 0.03239 ppl @ LLaMA-v1-7B", },
     { "F16",    LLAMA_FTYPE_MOSTLY_F16,    "14.00G, +0.0020 ppl @ Mistral-7B",  },
     { "BF16",   LLAMA_FTYPE_MOSTLY_BF16,   "14.00G, -0.0050 ppl @ Mistral-7B",  },
     { "F32",    LLAMA_FTYPE_ALL_F32,       "26.00G              @ 7B",          },