--- license: llama3 language: - tr - en model-index: - name: Kocdigital-LLM-8b-v0.1 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge TR type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc value: 44.03 name: accuracy - task: type: text-generation name: Text Generation dataset: name: HellaSwag TR type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc value: 46.73 name: accuracy - task: type: text-generation name: Text Generation dataset: name: MMLU TR type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 49.11 name: accuracy - task: type: text-generation name: Text Generation dataset: name: TruthfulQA TR type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: acc name: accuracy value: 48.21 - task: type: text-generation name: Text Generation dataset: name: Winogrande TR type: winogrande config: winogrande_xl split: validation args: num_few_shot: 10 metrics: - type: acc value: 54.98 name: accuracy - task: type: text-generation name: Text Generation dataset: name: GSM8k TR type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 51.78 name: accuracy ---