Hugging Face's logo

sleepdeprived3
/
Cydonia-24B-v2_EXL2_4bpw_H8

Safetensors
mistral
4-bit precision
exl2
Model card Files Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Model Card for Cydonia 24B v2 - Commando Edition

image/png

Support Me

Links

Description

Cydonia v2 builds upon the creative flair and adventure bias of its predecessors, offering enhanced capabilities and a more immersive experience. This version is fine-tuned to work seamlessly with Mistral V7 Tekken or Metharme chat templates, providing a versatile and engaging assistant for any task or roleplay scenario.

You may also like:

  • Cydonia v1: The legend that started it all and still a favorite for some
  • Cydonia v1.1: Less refusals, a more evil v1
  • Cydonia v1.2: Creative boost
  • Cydonia v1.3: Adventure Edition

image/png

Arsenal (Supported Chat Templates)

  • Metharme (a.k.a. Pygmalion in ST) for RP / Story
  • Mistral V7 Tekken for Instruct / RP / Story

Favorite RP Format

*action* Dialogue *thoughts* Dialogue *narration* in 1st person PoV

Thank you, Envoid! I cackled.

Key Features

  • Multilingual: Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch, and Polish.
  • Agent-Centric: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
  • Advanced Reasoning: State-of-the-art conversational and reasoning capabilities.
  • Apache 2.0 License: Open license allowing usage and modification for both commercial and non-commercial purposes.
  • Context Window: A 32k context window.
  • System Prompt: Maintains strong adherence and support for system prompts.
  • Tokenizer: Utilizes a Tekken tokenizer with a 131k vocabulary size.
Downloads last month
0
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.