M2411-123B-Animus-V14.0

Send me your support to help me feed the data beast! also taking comissions for universe specific models

Support on Ko-fi

Important: Chat Template

This model uses the Mistral V7 instruction template. Ensure your client is configured correctly to avoid degraded performance.

The space before each assistant message is part of the assistant turn (see Jinja template: ' ' + message['content']), not the user turn. Getting this wrong silently degrades the model rather than breaking it outright.

Human-Readable Format:

<s>[SYSTEM_PROMPT] system[/SYSTEM_PROMPT][INST] user[/INST] assistant</s>[INST] user[/INST]

✅ Chat Completion (recommended): Use your inference server's built-in chat template (llama.cpp, TabbyAPI, vllm, etc.). The space is handled automatically — no manual configuration needed.

⚠️ Text Completion: You must manage spacing manually:

• All completed assistant turns need a leading space: [/INST] response</s>
• The final [/INST] (generation prompt) must have no trailing space — the model generates its own leading space as its first token. Adding one causes a double-space token sequence the model was not trained on.
• In SillyTavern: set Assistant Prefix to (space), Last Assistant Prefix to {{trim}}, and enable Replace Macros in Sequences.

Jinja Template:

{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + '[/INST]' }}{% elif message['role'] == 'system' %}{{ '[SYSTEM_PROMPT] ' + message['content'] + '[/SYSTEM_PROMPT]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user, system and assistant roles are supported!') }}{% endif %}{% endfor %}

Quantized Models

The quantized model files are available for download. Click the buttons below to view the files.

Download GGUF Files → Download EXL3 Files →

Character Card & Lore Book

For the best roleplaying experience, it is highly recommended to use the provided character card and lore book. These files help guide the model's persona and provide rich, in-universe context.

Download Files →

Sampler Presets

For a seamless setup in SillyTavern, you can download pre-configured sampler presets. These are tuned to provide an optimal balance between creativity and narrative coherence for this model.

Simply download the .json file below and import it into SillyTavern's sampler presets menu.

Download SillyTavern Presets →

For those that dont use silly tavern, Samplers settings are:

Temperature: 1.0

Min P: 0.02

Roleplay Format Guide

For the best results, use this structured format. This helps the AI clearly distinguish between actions, inner thoughts, and dialogue.

Actions / Descriptions

*He walked across the room and stared out the window.*

Inner Thoughts

*-I wonder what she's thinking.-*

Dialogue

Alex (Curious): "What do you see out there?"

Standard novel-style formatting is also understood, but this structured format is preferred for clarity.

Roleplay Example

Click the button below to view a full, unedited chatlog demonstrating the model's narrative style and character portrayal.

View Chatlog Example →

Model Description

This is Version 14.0, in the Animus series. V14.0 is built on Mistral-Large-Instruct-2411 (123B), offering a massive leap in parameter count and underlying logic compared to previous versions.

V14.0's strength comes from a novel dataset designed to teach the model the why behind the lore, not just the what. The training data has been heavily expanded for this version:

• Base Samples Doubled: The foundation of in-character study sessions and uncensored roleplays has been doubled in size (14,000) to deepen contextual understanding.
• 1,000 Instruction Q&A Samples: Additional Wings of Fire-based instruction formatting.
• 1,000 NSFW/BAD Ending Samples: Non-Wings of Fire scenarios added to diversify narrative flexibility and handle darker, complex outcomes.

The result is a model with exceptionally strong prose and a deep grasp of in-universe lore, making for a highly immersive and accurate roleplaying experience.

Note for roleplay, it follows system prompt and first message, meaning if the first assistant message is short, the following messages will be short.

Training Details

V14.0 Training Process

V14.0 utilizes a comprehensive LoRA fine-tuning process on the Mistral 123B architecture.

• Base Model: Mistral-Large-Instruct-2411
• Hardware: 1x B200
• Training Time: 48 hours
• Epochs: 2
• Method: QLoRA

Training Dataset

The V14.0 dataset has been significantly expanded from previous versions:

• Doubled Base Dataset (14,000 examples): The original foundation of In-Character Q&A and Uncensored Roleplay examples was doubled to reinforce the lore foundation and enhance roleplay quality.
• Instruction Q&A (1,000 examples): Additional Wings of Fire-based instruction Q&A sets.
• NSFW / Bad Endings (1,000 examples): Non-Wings of Fire scenarios specifically targeting mature themes and bad endings to widen the model's range of dramatic narrative capabilities.

All datasets underwent a rigorous cleaning process to remove formatting artifacts, resulting in a cleaner and more natural narrative style.

Intended Use & Limitations

• Intended Use: The primary purpose of this model is for creative and roleplaying within the Wings of Fire universe. However, user feedback indicates it is also highly effective for general-purpose roleplaying.
• Limitations & Quirks:
  • Performance on tasks outside of its training domain (general knowledge, coding, etc.) is not guaranteed.
  • Versatility: While it is tuned for Wings of Fire, it is highly capable of performing roleplay in other settings and characters.
  • The model may generate plausible but non-canonical information when pushed outside the established "what-if" scenarios.
  • Content: The training data includes mature and darker themes from the Wings of Fire series. Standard responsible AI practices should be followed.
  • Safety: This model has not undergone additional safety alignment beyond what was included in its base model.

Acknowledgements

• Credit to Mistral AI for the powerful 123B base model.
• Credit to Google for the Gemini Pro model, used in dataset generation.
• Credit to Anthropic for sonnet 4.5, used in dataset generation.
• Credit to Hangzhou DeepSeek Artificial Intelligence for the deepseek model, used in dataset generation.
• Credit to Moonshot AI for the Kimi K2 model, used in dataset generation.