The model card, file list, and checksums are here. Have the files and permission to share them? Submit a torrent so others can download from peers.
Getting the source files requires Hugging Face approval.Send me your support to help me feed the data beast! also taking comissions for universe specific models
Support on Ko-fiThis model uses the standard Gemma 4 chat template. The structure is complex and requires specific configuration for correct performance. Please read the following sections carefully.
Human-Readable Format:
<bos><|turn>system
<|think|>
{system prompt}<turn|>
<|turn>user
{user message}<turn|>
<|turn>model
<|channel>thought
{reasoning}<channel|>{response}<turn|>
Strongly recommended: Always use the /v1/chat/completions endpoint. Correct formatting is handled automatically by the server.
Text completion (/v1/completions) is currently broken for impersonations without a custom patch. Sending the context as a user prompt and asking the model to generate the response can produce a malformed turn structure.
Reasoning with text completion and TabbyAPI/Llama.cpp specific: You must prefill the response with start_reply_with: <|channel>thought + \n (a new line) or reasoning will not trigger (you will get blank responses if you enabled reasoning and did not prefill)
When using an OpenAI-compatible API, you must add custom parameters to control thinking and ensure correct token handling. In frontends like SillyTavern, add the following JSON to the "Custom Parameters" (or extra_body) field in your connection settings:
"chat_template_kwargs": {"enable_thinking": true}
"skip_special_tokens": false
"enable_thinking": true: Activates the model's chain-of-thought reasoning. Change to false to disable it for faster, more direct responses."skip_special_tokens": false: This is critical. It prevents the API from stripping away the special tokens (like <|channel> and <channel|>) that are required for the model's chat template to work correctly.enable_thinking to select at runtime.<|think|> token in the system turn is what activates chain-of-thought reasoning at the architecture level.The quantized model files are available for download. Click the button below to view the files.
Download GGUF Files → Download EXL3 Files →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 →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.
Temperature: 1.0
Min P: 0.02
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.
Click the button below to view a full, unedited chatlog demonstrating the model's narrative style and character portrayal.
View Chatlog Example →This is Version 14.1, in the Animus series. V14.1 is built on google/gemma-4-26B-A4B-it, offering a massive leap in parameter count and underlying logic compared to previous versions.
V14.1'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:
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.
V14.1 Was Fully fine-tuned with the vison layers frozen, and not is not a Lora adapter.
The V14.0 dataset has been significantly expanded from previous versions:
All datasets underwent a rigorous cleaning process to remove formatting artifacts, resulting in a cleaner and more natural narrative style.
**scene transitions**. The model should now produce cleaner prose.model-00003-of-00007.safetensors 8.2 GBmodel-00004-of-00007.safetensors 8.2 GBmodel-00005-of-00007.safetensors 8.2 GBmodel-00006-of-00007.safetensors 8.2 GBmodel-00002-of-00007.safetensors 8.2 GBmodel-00001-of-00007.safetensors 8.1 GBmodel-00007-of-00007.safetensors 4.1 GB