Fixes for docs (mlcommons#2334)

Author: anandhu-eng

docs/benchmarks/language/scc25_guide/scc25.md

@@ -58,15 +58,11 @@ or supporting multi-node execution) useful for the community and [MLCommons](htt
 
 {{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "reference", fixed_scenarios=["Offline"], categories=["Datacenter"], setup_tips=False, implementation_tips=False, skip_test_query_count=True) }}
 
-{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "reference", fixed_scenarios=["Offline"], categories=["Datacenter"], setup_tips=False, implementation_tips=False, skip_test_query_count=True) }}
-
 === "Nvidia"
     ## Nvidia MLPerf Implementation
 
 {{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "nvidia", fixed_scenarios=["Offline"], categories=["Datacenter"], setup_tips=False, implementation_tips=False, skip_test_query_count=True) }}
 
-{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.99", "nvidia", fixed_scenarios=["Offline"], categories=["Datacenter"], setup_tips=False, implementation_tips=False, skip_test_query_count=True) }}
-
 ## Submission Commands
 
 ### Generate actual submission tree

main.py

@@ -786,7 +786,6 @@ def mlperf_inference_run_command(
             if "llama2-70b" in model.lower():
                 if implementation == "nvidia":
                     cmd_suffix += f" \\\n{pre_space} --tp_size=<TP_SIZE>"
-                    cmd_suffix += f" \\\n{pre_space} --nvidia_llama2_dataset_file_path=<PATH_TO_PICKE_FILE>"
                 elif implementation == "neuralmagic":
                     cmd_suffix += f" \\\n{pre_space} --api_server=http://localhost:8000"
                     cmd_suffix += f" \\\n{pre_space} --vllm_model_name=nm-testing/Llama-2-70b-chat-hf-FP8"