Steelskull/Q2.5-MS-Mistoria-72b

TEXT GENERATIONConcurrency Cost:4Model Size:72.7BQuant:FP8Ctx Length:32kArchitecture:Transformer0.0K Cold

Steelskull/Q2.5-MS-Mistoria-72b is a 72.7 billion parameter language model developed by Steelskull, built upon the Qwen 2.5 architecture. This model is a merge of multiple base models, including EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1, ZeusLabs/Chronos-Platinum-72B, and shuttleai/shuttle-3. It is specifically designed to enhance robust storytelling capabilities while maintaining overall intelligence, making it suitable for complex narrative generation and conversational AI tasks.

Loading preview...

Q2.5-MS-Mistoria-72b: Merged Storytelling and Intelligence

Steelskull's Q2.5-MS-Mistoria-72b is a substantial 72.7 billion parameter language model, leveraging the Qwen 2.5 architecture. This model represents Steelskull's initial foray into the 72B parameter space, with a core objective to combine the strong storytelling abilities of various models while preserving high levels of intelligence.

Key Characteristics

  • Base Architecture: Built on the Qwen 2.5 framework.
  • Merged Design: It is a composite model, integrating components from:
    • EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
    • ZeusLabs/Chronos-Platinum-72B
    • shuttleai/shuttle-3
  • Primary Goal: Optimized for robust storytelling and maintaining intelligence across diverse tasks.
  • Context Length: Features a notable context length of 131,072 tokens.
  • Usage Format: Designed to be used with the Qwen format.

Use Cases

This model is particularly well-suited for applications requiring:

  • Advanced Narrative Generation: Creating detailed and coherent stories or long-form content.
  • Complex Conversational AI: Engaging in extended, intelligent dialogues where context and narrative flow are crucial.
  • Creative Writing Assistance: Aiding in the development of intricate plots and character interactions.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p