wadah/DeciLM-6b-GGML

license:

• llama2
• other datasets:
• cerebras/SlimPajama-627B language:
• en pipeline_tag: text-generation tags:
• Deci AI
• DeciLM model-index:
• name: DeciLM 6B results:
  • task: type: text-generation dataset: type: ai2/arc name: ai2_arc metrics:
    • name: ARC Challenge type: ARC Challenge value: 42.06 verified: false
  • task: type: text-generation dataset: type: ai2/arc name: ai2_arc metrics:
    • name: ARC Easy type: ARC Easy value: 70.02 verified: false
  • task: type: text-generation dataset: type: boolq name: boolq metrics:
    • name: BoolQ type: BoolQ value: 71.01 verified: false
  • task: type: text-generation dataset: type: hellaswag name: hellaswag metrics:
    • name: HellaSwag type: HellaSwag value: 74.58 verified: false
  • task: type: text-generation dataset: type: LAMBDA name: OpenAI LAMBDA metrics:
    • name: LAMBDA type: LAMBDA value: 69.78 verified: false
  • task: type: text-generation dataset: type: OpenBookQA name: openbookqa metrics:
    • name: OpenBookQA type: OpenBookQA value: 34 verified: false
  • task: type: text-generation dataset: type: PIQA name: piqa metrics:
    • name: PIQA type: PIQA value: 77.09 verified: false
  • task: type: text-generation dataset: type: truthful_qa name: truthful_qa metrics:
    • name: TruthfulQA type: TruthfulQA value: 36.19 verified: false
  • task: type: text-generation dataset: type: winogrande name: winogrande metrics:
    • name: Winogrande type: Winogrande value: 68.03 verified: false