Merge pull request #9 from anandhu-eng/cm_readme_inference_update

Cm readme inference update

docs/benchmarks/image_classification/get-resnet50-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Image Classification using ResNet50 
 
 ## Dataset

docs/benchmarks/image_classification/mobilenets.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Image Classification using Mobilenet models
 
 Mobilenet models are not official MLPerf models and so cannot be used for a Closed division MLPerf inference submission. But since they can be run with Imagenet dataset, we are allowed to use them for Open division submission. Only CPU runs are supported now. 

docs/benchmarks/image_classification/resnet50.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Image Classification using ResNet50 
 
 === "MLCommons-Python"

docs/benchmarks/language/bert.md

@@ -1,36 +1,34 @@
+---
+hide:
+  - toc
+---
+
 # Question Answering using Bert-Large
 
 === "MLCommons-Python"
     ## MLPerf Reference Implementation in Python
 
-    BERT-99
 {{ mlperf_inference_implementation_readme (4, "bert-99", "reference") }}
 
-    BERT-99.9
 {{ mlperf_inference_implementation_readme (4, "bert-99.9", "reference") }}
 
 === "Nvidia"
     ## Nvidia MLPerf Implementation
 
-    BERT-99
 {{ mlperf_inference_implementation_readme (4, "bert-99", "nvidia") }}
 
-    BERT-99.9
 {{ mlperf_inference_implementation_readme (4, "bert-99.9", "nvidia") }}
 
 === "Intel"
     ## Intel MLPerf Implementation
-    BERT-99
+
 {{ mlperf_inference_implementation_readme (4, "bert-99", "intel") }}
 
-    BERT-99.9
 {{ mlperf_inference_implementation_readme (4, "bert-99.9", "intel") }}
 
 === "Qualcomm"
     ## Qualcomm AI100 MLPerf Implementation
 
-    BERT-99
 {{ mlperf_inference_implementation_readme (4, "bert-99", "qualcomm") }}
 
-    BERT-99.9
 {{ mlperf_inference_implementation_readme (4, "bert-99.9", "qualcomm") }}

docs/benchmarks/language/get-bert-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Question Answering using Bert-Large
 
 ## Dataset

docs/benchmarks/language/get-gptj-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Text Summarization using GPT-J
 
 ## Dataset

docs/benchmarks/language/get-llama2-70b-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Text Summarization using LLAMA2-70b
 
 ## Dataset
@@ -23,4 +28,8 @@ Get the Official MLPerf LLAMA2-70b Model
     ```
     cm run script --tags=get,ml-model,llama2-70b,_pytorch -j
     ```
+
+!!! tip
+
+    Downloading llama2-70B model from Hugging Face will prompt you to enter the Hugging Face username and password. Please note that the password required is the [**access token**](https://huggingface.co/settings/tokens) generated for your account. Additionally, ensure that your account has access to the [llama2-70B](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) model.
 

docs/benchmarks/language/get-mixtral-8x7b-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 ## Dataset
 
 The benchmark implementation run command will automatically download the preprocessed validation and calibration datasets. In case you want to download only the datasets, you can use the below commands.

docs/benchmarks/language/gpt-j.md

@@ -1,39 +1,38 @@
+---
+hide:
+  - toc
+---
+
 # Text Summarization using GPT-J
 
 
 === "MLCommons-Python"
     ## MLPerf Reference Implementation in Python
-
-    GPT-J-99
+
 
 {{ mlperf_inference_implementation_readme (4, "gptj-99", "reference") }}
 
-    GPTJ-99.9
 
 {{ mlperf_inference_implementation_readme (4, "gptj-99.9", "reference") }}
 
 === "Nvidia"
     ## Nvidia MLPerf Implementation
 
-    GPTJ-99
 
 {{ mlperf_inference_implementation_readme (4, "gptj-99", "nvidia") }}
 
-    GPTJ-99.9
 
 {{ mlperf_inference_implementation_readme (4, "gptj-99.9", "nvidia") }}
 
 === "Intel"
     ## Intel MLPerf Implementation
-    GPTJ-99
 
 {{ mlperf_inference_implementation_readme (4, "gptj-99", "intel") }}
 
 
 === "Qualcomm"
     ## Qualcomm AI100 MLPerf Implementation
 
-    GPTJ-99
 
 {{ mlperf_inference_implementation_readme (4, "gptj-99", "qualcomm") }}
 

docs/benchmarks/language/llama2-70b.md

@@ -1,28 +1,28 @@
+---
+hide:
+  - toc
+---
+
 # Text Summarization using LLAMA2-70b
 
 
 === "MLCommons-Python"
     ## MLPerf Reference Implementation in Python
 
-    LLAMA2-70b-99
 {{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "reference") }}
 
-    LLAMA2-70b-99.9
 {{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "reference") }}
 
 === "Nvidia"
     ## Nvidia MLPerf Implementation
 
-    LLAMA2-70b-99
 {{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "nvidia") }}
 
-    LLAMA2-70b-99.9
 {{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "nvidia") }}
 
+=== "Neural Magic"
+    ## Neural Magic MLPerf Implementation
+
+{{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "neuralmagic") }}
 
-=== "Qualcomm"
-    ## Qualcomm AI100 MLPerf Implementation
-
-    LLAMA2-70b-99
-{{ mlperf_inference_implementation_readme (4, "llama2-70b-99", "qualcomm") }}
-
+{{ mlperf_inference_implementation_readme (4, "llama2-70b-99.9", "neuralmagic") }}

docs/benchmarks/language/mixtral-8x7b.md

@@ -1,6 +1,9 @@
+---
+hide:
+  - toc
+---
 
 === "MLCommons-Python"
     ## MLPerf Reference Implementation in Python
 
-    MIXTRAL-8x7b
 {{ mlperf_inference_implementation_readme (4, "mixtral-8x7b", "reference") }}

docs/benchmarks/medical_imaging/3d-unet.md

@@ -1,33 +1,32 @@
+---
+hide:
+  - toc
+---
+
 # Medical Imaging using 3d-unet (KiTS 2019 kidney tumor segmentation task)
 
 
 === "MLCommons-Python"
     ## MLPerf Reference Implementation in Python
 
-    3d-unet-99
 
 {{ mlperf_inference_implementation_readme (4, "3d-unet-99", "reference") }}
 
-    3d-unet-99.9
 
 {{ mlperf_inference_implementation_readme (4, "3d-unet-99.9", "reference") }}
 
 === "Nvidia"
     ## Nvidia MLPerf Implementation
-    3d-unet-99
 
 {{ mlperf_inference_implementation_readme (4, "3d-unet-99", "nvidia") }}
 
-    3d-unet-99.9
 
 {{ mlperf_inference_implementation_readme (4, "3d-unet-99.9", "nvidia") }}
 
 === "Intel"
     ## Intel MLPerf Implementation
-    3d-unet-99
 
 {{ mlperf_inference_implementation_readme (4, "3d-unet-99", "intel") }}
 
-    3d-unet-99.9
 
 {{ mlperf_inference_implementation_readme (4, "3d-unet-99.9", "intel") }}

docs/benchmarks/medical_imaging/get-3d-unet-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Medical Imaging using 3d-unet (KiTS 2019 kidney tumor segmentation task)
 
 ## Dataset
@@ -7,9 +12,14 @@ The benchmark implementation run command will automatically download the validat
 === "Validation"
     3d-unet validation run uses the KiTS19 dataset performing [KiTS 2019](https://kits19.grand-challenge.org/) kidney tumor segmentation task
 
-    ### Get Validation Dataset
+    ### Get Validation Dataset(Original)
+    ```
+    cm run script --tags=get,dataset,kits19,_validation -j
+    ```
+
+    ### Get Validation Dataset(Preprocessed)
     ```
-    cm run script --tags=get,dataset,kits19,validation -j
+    cm run script --tags=get,dataset,kits19,preprocessed -j
     ```
 
 ## Model

docs/benchmarks/object_detection/get-retinanet-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Object Detection using Retinanet
 
 ## Dataset

docs/benchmarks/object_detection/retinanet.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Object Detection using Retinanet
 
 === "MLCommons-Python"

docs/benchmarks/recommendation/dlrm-v2.md

@@ -1,22 +1,29 @@
+---
+hide:
+  - toc
+---
+
 # Recommendation using DLRM v2
 
 
 ## Benchmark Implementations
 === "MLCommons-Python"
     ## MLPerf Reference Implementation in Python
 
-    DLRM-v2-99
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "reference") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "reference") }}
 
-    DLRM-v2-99.9
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "reference") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "reference") }}
 
 === "Nvidia"
     ## Nvidia MLPerf Implementation
-
-    DLRM-v2-99
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99", "nvidia") }}
 
-    DLRM-v2-99.9
-{{ mlperf_inference_implementation_readme (4, "dlrm_v2-99.9", "nvidia") }}
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "nvidia") }}
+
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "nvidia") }}
+
+=== "Intel"
+    ## Intel MLPerf Implementation
+
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99", "intel") }}
 
+{{ mlperf_inference_implementation_readme (4, "dlrm-v2-99.9", "intel") }}

docs/benchmarks/recommendation/get-dlrm_v2-data.md → docs/benchmarks/recommendation/get-dlrm-v2-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Recommendation using DLRM v2
 
 ## Dataset
@@ -9,7 +14,7 @@ The benchmark implementation run command will automatically download the validat
 
     ### Get Validation Dataset
     ```
-    cm run script --tags=get,dataset,criteo,validation -j
+    cm run script --tags=get,dataset,criteo,_validation -j
     ```
 ## Model
 The benchmark implementation run command will automatically download the required model and do the necessary conversions. In case you want to only download the official model, you can use the below commands.
@@ -20,6 +25,6 @@ Get the Official MLPerf DLRM v2 Model
 
     ### Pytorch
     ```
-    cm run script --tags=get,ml-model,dlrm_v2,_pytorch -j
+    cm run script --tags=get,ml-model,dlrm,_pytorch -j
     ```
 

docs/benchmarks/text_to_image/get-sdxl-data.md

@@ -1,3 +1,8 @@
+---
+hide:
+  - toc
+---
+
 # Text to Image using Stable Diffusion
 
 ## Dataset