model_card.yaml

---
language:
- en
license: apache-2.0
library_name: peft
tags:
- text-generation-inference
- logical-reasoning
- chat
- text
- conversational
- persona
- reasoning
- LLM
- vanta-research
- apollo-astralis
- large-language-model
- collaborative-ai
- conversational-ai
- lora
- mistral
- ministral
- apache

base_model: Ministral-3-8B-Reasoning-2512
pipeline_tag: text-generation
datasets:
- custom
metrics:
- accuracy
model-index:
- name: Apollo Astralis 2
  results:
  - task:
      type: question-answering
      name: Physical Commonsense Reasoning
    dataset:
      type: piqa
      name: PIQA
    metrics:
    - type: accuracy
      value: 90.0
      name: Accuracy
  - task:
      type: question-answering
      name: Coreference Resolution
    dataset:
      type: winogrande
      name: WinoGrande
    metrics:
    - type: accuracy
      value: 40.0
      name: Accuracy
  - task:
      type: question-answering
      name: Commonsense Reasoning
    dataset:
      type: commonsenseqa
      name: CommonsenseQA
    metrics:
    - type: accuracy
      value: 70.0
      name: Accuracy