Remove MPT-30B until huggingface model link is back (#126)

Author: EricKing626

benchmark/llm-foundry/mpt-30b/README.md

@@ -1819,23 +1819,6 @@
     "args":
      "--model_repo deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --test_option latency --num_gpu 8 --datatype bfloat16 --dataset random --batch_size 1,8,32 --lat_input_output_len '128:128;128:1024;1024:128;1024:1024'"
   },
-  {
-    "name": "pyt_mpt30b_training",
-    "dockerfile": "docker/pyt_mpt30b_training",
-    "scripts": "scripts/pyt_mpt30b_training/run.sh",
-    "n_gpus": "-1",
-    "owner": "mad.support@amd.com",
-    "training_precision": "",
-    "tags": [
-      "training",
-      "pyt",
-      "mosaic",
-      "composer"
-    ],
-    "timeout": -1,
-    "args":
-    "--model_repo mosaicml/mpt-30b --test_option throughput --tunableop off"
-  },
   {
     "name": "pyt_hy_video",
     "url": "",