LLamaRecipes/tools/benchmarks/inference/cloud/aws/fmbench/config.yml

general:
  name: "llama2-7b-v1"      
  model_name: "Llama2-7b"
  
# AWS and SageMaker settings
aws:
  # AWS region, this parameter is templatized, no need to change
  region: {region}
  # SageMaker execution role used to run FMBench, this parameter is templatized, no need to change
  sagemaker_execution_role: {role_arn}
  # S3 bucket to which metrics, plots and reports would be written to
  bucket: {write_bucket}

# directory paths in the write bucket, no need to change these
dir_paths:
  data_prefix: data
  prompts_prefix: prompts
  all_prompts_file: all_prompts.csv
  metrics_dir: metrics
  models_dir: models
  metadata_dir: metadata

# S3 information for reading datasets, scripts and tokenizer
s3_read_data:
  # read bucket name, templatized, if left unchanged will default to sagemaker-fmbench-read-<region>-<account_id>
  read_bucket: {read_bucket}
  scripts_prefix: scripts
  
  # S3 prefix in the read bucket where deployment and inference scripts should be placed
  scripts_prefix: scripts
    
  # deployment and inference script files to be downloaded are placed in this list
  # only needed if you are creating a new deployment script or inference script
  # your HuggingFace token does need to be in this list and should be called "hf_token.txt"
  script_files:
  - hf_token.txt

  # configuration files (like this one) are placed in this prefix
  configs_prefix: configs

  # list of configuration files to download, for now only pricing.yml needs to be downloaded
  config_files:
  - pricing.yml

  # S3 prefix for the dataset files
  source_data_prefix: source_data
  # list of dataset files, the list below is from the LongBench dataset https://huggingface.co/datasets/THUDM/LongBench
  source_data_files:
  - 2wikimqa_e.jsonl
  - 2wikimqa.jsonl
  - hotpotqa_e.jsonl
  - hotpotqa.jsonl
  - narrativeqa.jsonl
  - triviaqa_e.jsonl
  - triviaqa.jsonl
  # S3 prefix for the tokenizer to be used with the models
  # NOTE 1: the same tokenizer is used with all the models being tested through a config file
  # NOTE 2: place your model specific tokenizers in a prefix named as <model_name>_tokenizer
  #         so the mistral tokenizer goes in mistral_tokenizer, Llama2 tokenizer goes in llama2_tokenizer and so on and so forth.
  tokenizer_prefix: tokenizer
  
  # S3 prefix for prompt templates
  prompt_template_dir: prompt_template

  # prompt template to use, NOTE: same prompt template gets used for all models being tested through a config file
  # the FMBench repo already contains a bunch of prompt templates so review those first before creating a new one
  prompt_template_file: prompt_template_llama2.txt

# steps to run, usually all of these would be
# set to yes so nothing needs to change here
# you could, however, bypass some steps for example
# set the 2_deploy_model.ipynb to no if you are re-running
# the same config file and the model is already deployed
run_steps:
  0_setup.ipynb: yes
  1_generate_data.ipynb: yes
  2_deploy_model.ipynb: yes
  3_run_inference.ipynb: yes
  4_model_metric_analysis.ipynb: yes
  5_cleanup.ipynb: yes


datasets:
  # Refer to the 1_generate_data.ipynb notebook
  # the dataset you use is expected to have the 
  # columns you put in prompt_template_keys list
  # and your prompt template also needs to have
  # the same placeholders (refer to the prompt template folder)
  prompt_template_keys:
  - input
  - context
  
  # if your dataset has multiple languages and it has a language
  # field then you could filter it for a language. Similarly,
  # you can filter your dataset to only keep prompts between
  # a certain token length limit (the token length is determined
  # using the tokenizer you provide in the tokenizer_prefix prefix in the
  # read S3 bucket). Each of the array entries below create a payload file
  # containing prompts matching the language and token length criteria.
  filters:
  - language: en    
    min_length_in_tokens: 1
    max_length_in_tokens: 500
    payload_file: payload_en_1-500.jsonl
  - language: en
    min_length_in_tokens: 500
    max_length_in_tokens: 1000
    payload_file: payload_en_500-1000.jsonl
  - language: en
    min_length_in_tokens: 1000
    max_length_in_tokens: 2000
    payload_file: payload_en_1000-2000.jsonl
  - language: en
    min_length_in_tokens: 2000
    max_length_in_tokens: 3000
    payload_file: payload_en_2000-3000.jsonl
  - language: en
    min_length_in_tokens: 3000
    max_length_in_tokens: 3840
    payload_file: payload_en_3000-3840.jsonl

# While the tests would run on all the datasets
# configured in the experiment entries below but 
# the price:performance analysis is only done for 1
# dataset which is listed below as the dataset_of_interest
metrics:
  dataset_of_interest: en_2000-3000

# all pricing information is in the pricing.yml file
# this file is provided in the repo. You can add entries
# to this file for new instance types and new Bedrock models
pricing: pricing.yml

# inference parameters, these are added to the payload
# for each inference request. The list here is not static
# any parameter supported by the inference container can be
# added to the list. Put the sagemaker parameters in the sagemaker
# section, bedrock parameters in the bedrock section (not shown here).
# Use the section name (sagemaker in this example) in the inference_spec.parameter_set
# section under experiments.
inference_parameters:
  sagemaker:
    do_sample: yes
    temperature: 0.1
    top_p: 0.92
    top_k: 120  
    max_new_tokens: 100
    return_full_text: False

# Configuration for experiments to be run. The experiments section is an array
# so more than one experiments can be added, these could belong to the same model
# but different instance types, or different models, or even different hosting
# options (such as one experiment is SageMaker and the other is Bedrock).
experiments:
  - name: llama2-7b-g5.xlarge-huggingface-pytorch-tgi-inference-2.0.1-tgi1.1.0
    # model_id is interpreted in conjunction with the deployment_script, so if you
    # use a JumpStart model id then set the deployment_script to jumpstart.py.
    # if deploying directly from HuggingFace this would be a HuggingFace model id
    # see the DJL serving deployment script in the code repo for reference.
    model_id: meta-textgeneration-llama-2-7b-f
    model_version: "3.*"
    model_name: llama2-7b-f
    ep_name: llama-2-7b-g5xlarge
    instance_type: "ml.g5.xlarge"
    image_uri: '763104351884.dkr.ecr.{region}.amazonaws.com/huggingface-pytorch-tgi-inference:2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04'
    deploy: yes
    instance_count: 1
    # FMBench comes packaged with multiple deployment scripts, such as scripts for JumpStart
    # scripts for deploying using DJL DeepSpeed, tensorRT etc. You can also add your own.
    # See repo for details    
    deployment_script: jumpstart.py
    # FMBench comes packaged with multiple inference scripts, such as scripts for SageMaker
    # and Bedrock. You can also add your own. See repo for details
    inference_script: sagemaker_predictor.py
    inference_spec:
      # this should match one of the sections in the inference_parameters section above
      parameter_set: sagemaker
    # runs are done for each combination of payload file and concurrency level
    payload_files:
    - payload_en_1-500.jsonl
    - payload_en_500-1000.jsonl
    - payload_en_1000-2000.jsonl
    - payload_en_2000-3000.jsonl
    #- payload_en_3000-3840.jsonl
    # concurrency level refers to number of requests sent in parallel to an endpoint
    # the next set of requests is sent once responses for all concurrent requests have
    # been received.
    concurrency_levels:
    - 1
    - 2
    - 4

    accept_eula: true
    # Environment variables to be passed to the container
    # this is not a fixed list, you can add more parameters as applicable.
    env:
      SAGEMAKER_PROGRAM: "inference.py"
      ENDPOINT_SERVER_TIMEOUT: "3600"
      MODEL_CACHE_ROOT: "/opt/ml/model"
      SAGEMAKER_ENV: "1"
      HF_MODEL_ID: "/opt/ml/model"
      MAX_INPUT_LENGTH: "4095"
      MAX_TOTAL_TOKENS: "4096"
      SM_NUM_GPUS: "1"
      SAGEMAKER_MODEL_SERVER_WORKERS: "1"

  - name: llama2-7b-g5.2xlarge-huggingface-pytorch-tgi-inference-2.0.1-tgi1.1.0
    # model_id is interpreted in conjunction with the deployment_script, so if you
    # use a JumpStart model id then set the deployment_script to jumpstart.py.
    # if deploying directly from HuggingFace this would be a HuggingFace model id
    # see the DJL serving deployment script in the code repo for reference. 
    model_id: meta-textgeneration-llama-2-7b-f
    model_version: "3.*"
    model_name: llama2-7b-f
    ep_name: llama-2-7b-g5-2xlarge
    instance_type: "ml.g5.2xlarge"
    image_uri: '763104351884.dkr.ecr.{region}.amazonaws.com/huggingface-pytorch-tgi-inference:2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04'
    deploy: yes
    # FMBench comes packaged with multiple deployment scripts, such as scripts for JumpStart
    # scripts for deploying using DJL DeepSpeed, tensorRT etc. You can also add your own.
    # See repo for details
    instance_count: 1
    deployment_script: jumpstart.py
    # FMBench comes packaged with multiple inference scripts, such as scripts for SageMaker
    # and Bedrock. You can also add your own. See repo for details
    inference_script: sagemaker_predictor.py
    inference_spec:
      # this should match one of the sections in the inference_parameters section above
      parameter_set: sagemaker
    # runs are done for each combination of payload file and concurrency level
    payload_files:
    - payload_en_1-500.jsonl
    - payload_en_500-1000.jsonl
    - payload_en_1000-2000.jsonl
    - payload_en_2000-3000.jsonl
    #- payload_en_3000-3840.jsonl
    
    # concurrency level refers to number of requests sent in parallel to an endpoint
    # the next set of requests is sent once responses for all concurrent requests have
    # been received.
    concurrency_levels:
    - 1
    - 2
    - 4
    # Added for models that require accepting a EULA
    accept_eula: true
    # Environment variables to be passed to the container
    # this is not a fixed list, you can add more parameters as applicable.
    env:
      SAGEMAKER_PROGRAM: "inference.py"
      ENDPOINT_SERVER_TIMEOUT: "3600"
      MODEL_CACHE_ROOT: "/opt/ml/model"
      SAGEMAKER_ENV: "1"
      HF_MODEL_ID: "/opt/ml/model"
      MAX_INPUT_LENGTH: "4095"
      MAX_TOTAL_TOKENS: "4096"
      SM_NUM_GPUS: "1"
      SAGEMAKER_MODEL_SERVER_WORKERS: "1"

# parameters related to how the final report is generated
report:
  # constraints for latency, cost and error rate
  # an experiment is considered successful or eligible for
  # selection for a use-case if it satisfies all of the following
  # constraints. Experiments are scored as per this criteria
  # higher score is better (see 4_model_metric_analysis.ipynb score_run function)
  latency_budget: 2
  cost_per_10k_txn_budget: 20
  error_rate_budget: 0
  # other misc reporting parameters, see 4_model_metric_analysis.ipynb
  # for more information
  per_inference_request_file: per_inference_request_results.csv
  all_metrics_file: all_metrics.csv
  txn_count_for_showing_cost: 10000
  v_shift_w_single_instance: 0.025
  v_shift_w_gt_one_instance: 0.025