gistfile1.txt

  - name: Llama 3.1 Instruct
    displayName: Llama 3.1 Instruct
    modelHubID: llama-3.1-instruct
    category: Text Generation
    type: HF
    description: The Llama 3.1 8B-Instruct, 8B instruct and 8B base NIM simplifies the deployment of the Llama 3.1 70B-Instruct, 8B instruct and 8B base tuned models which is optimized for language understanding, reasoning, and text generation use cases, and outperforms many of the available open source chat models on common industry benchmarks.
    requireLicense: True
    licenseAgreements:
    - label: Use Policy
      url: https://llama.meta.com/llama3/use-policy/
    - label: License Agreement
      url: https://llama.meta.com/llama3/license/
    modelVariants:
      - variantId: Llama 3.1 8B Instruct
        source:URL: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/llama-3_1-70b-instruct-nemo
        optimizationProfiles:
        - profileId: meta-llama/Llama-3.1-8B-instruct
          framework: TensorRT-LLM
          displayName: Llama 3.1 70B Instruct A100 BF16 ThroughputLoRA
          latestVersionSizeInBytes: 149093153785
          modelFormat: trl-llm
          spec:
          - key: PROFILE
            value: Throughput
          - key: PRECISION
            value: BF16
          - key: GPU
            value: A100
          - key: COUNT
            value: 4
          - key: GPU DEVICE
            value: 20b2:10de