test

test.yaml

models:
  - name: Llama-2-Chat
    displayName: Llama-2-Chat (Before 24.02)
    description: Llama-2-Chat model published by Meta
    versions:
      - latestVersionId: LLAMA-2-70B-CHAT
        sha: ff6d1c3ba37b31d4af421951c2300f2256fb3691
        latestVersionSizeInBytes: 107224858679
        createdDate: 2023-10-24T18:21:04.610Z
        updatedDate: 2024-04-23T22:57:49.590Z
        metadata:
          - OptimizationDetails:
              Artifactname: LLAMA-2-70B-CHAT-4K-FP16-4-A100.24.01
              framework: TensorRT-LLM
              modelFormat: trt_llm
              precision: float16
              libraryName: transformers
              hardware:
                GPU: A100
                Count: 2
              NIMVersion: 24.01
          - OptimizationDetails:
              Artifactname: LLAMA-2-70B-CHAT-4K-int8-4-A100.24.01
              framework: TensorRT-LLM
              modelFormat: trt_llm
              precision: int8
              libraryName: transformers
              hardware:
                GPU: A100
                Count: 2
              NIMVersion: 24.01 
      - latestVersionId: LLAMA-2-13B-CHAT
        sha: ff6d1c3ba37b31d4af421951c2300f2256fb3691
        latestVersionSizeInBytes: 107224858679
        createdDate: 2023-10-24T18:21:04.610Z
        updatedDate: 2024-04-23T22:57:49.590Z
        metadata:
          - OptimizationDetails:
              Artifactname: LLAMA-2-70B-CHAT-4K-int8-4-A100.24.01
              framework: TensorRT-LLM
              modelFormat: trt_llm
              precision: int8
              libraryName: transformers
              hardware:
                GPU: A100
                Count: 2
              NIMVersion: 24.01
    labels:
      - Large Language Model
      - TensorRT-LLM
      - Language Generation
      - NeMo
      - NVIDIA Validated
      - data labeling
    publisher:
      author: authroname
      name: Meta
      URL: www.facebookreseach.com
    group:
      - llama
      - meta
    tags:
      - auto_model: AutoModelForCausalLM
      - pipeline_tag: text-generation
      - processor: AutoTokenizer
    config:
      architectures:
        - LlamaForCausalLM
      model_type: llama
    Tasks:
      - Language Generation
      - Data Labeling
    license: cc-by-nc-4.0
    source: https://huggingface.co/meta-llama/Meta-Llama-3-8B
    language:
      - en
  - name: GPT-3.5-Turbo
    displayName: GPT-3.5-Turbo (Stable)
    description: GPT-3.5-Turbo model published by OpenAI
    version:
      latestVersionId: GPT-3.5-TURBO
      sha: d54e9c2b0f4a3c9fb8f23c2c3e4298e3f8d5a8b9
      latestVersionSizeInBytes: 65432109876
      createdDate: 2023-09-10T14:15:22.123Z
      updatedDate: 2024-02-12T20:35:10.456Z
      metadata:
          - OptimizationDetails:
              Artifactname: GPT-3.5-TURBO-CHAT-4K-int8-4-A100.24.01
              framework: TensorRT-LLM
              modelFormat: trt_llm
              precision: int8
              libraryName: transformers
              hardware:
                GPU: A100
                Count: 2
              NIMVersion: 24.01
    labels:
      - Large Language Model
      - TensorRT-LLM
      - Language Generation
      - Chatbot
      - OpenAI Validated
    publisher:
      author: openai_author
      name: OpenAI
      URL: www.openai.com
    group:
      - gpt
      - openai
    tags:
      - auto_model: AutoModelForCausalLM
      - pipeline_tag: text-generation
      - processor: AutoTokenizer
    config:
      architectures:
        - GPTForCausalLM
      model_type: gpt
    Tasks:
      - Language Generation
      - Chatbot
    license: proprietary
    source: https://huggingface.co/openai/GPT-3.5-Turbo
    language:
      - en