darkhn-quants-2/ministral-3-8b-animus-v12.0-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "tags": [
      "finetune",
      "roleplay",
      "chat",
      "wings-of-fire",
      "nsfw",
      "not-for-all-audiences"
    ],
    "base_model": [
      "Darkhn/Ministral-3-8B-Animus-V12.0"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "tags": [
        "finetune",
        "roleplay",
        "chat",
        "wings-of-fire",
        "nsfw",
        "not-for-all-audiences"
      ],
      "base_model": [
        "Darkhn/Ministral-3-8B-Animus-V12.0"
      ]
    },
    "hero_image_url": "image.png",
    "summary": "body { font-family: 'Quicksand', sans-serif; background: linear-gradient(135deg, #4a1e00 0%, #1c0a00 100%); color: #F5EFE6; margin: 0; padding: 0; font-size: 16px; } h1, h2, h3, h4, summary { font-family: 'Cinzel', serif; } .container { margin: 20px auto; max-width: 900px; background-color: rgba(28, 22, 18, 0.95); padding: 30px; border-radius: 12px; box-shadow: 0 4px 20px rgba(255, 140, 0, 0.15); border: 1px solid rgba(255, 140, 0, 0.2); outline: 1px solid rgba(255, 140, 0, 0.5); outline-offset: -1px; position: relative; } .container::before { content: ''; position: absolute; top: -1px; left: -1px; right: -1px; bottom: -1px; border: 1px solid rgba(255, 165, 0, 0.98); border-radius: 12px; pointer-events: none; animation: borderGlow 2.5s ease-in-out infinite; } @keyframes borderGlow { 0% { box-shadow: 0 0 5px rgba(255, 165, 0, 0.98); } 50% { box-shadow: 0 0 12px rgba(255, 165, 0, 0.98); } 100% { box-shadow: 0 0 5px rgba(255, 165, 0, 0.98); } } .header h1 { font-size: 32px; color: #FFA500; margin: 0 0 20px 0; text-align: center; text-shadow: 0 0 12px rgba(255, 100, 0, 0.6); } .info img { width: 100%; max-width: 700px; display: block; margin: 0 auto 25px auto; border-radius: 10px; box-shadow: 0 0 20px rgba(255, 140, 0, 0.25); border: 1px solid rgba(255, 140, 0, 0.2); outline: 1px solid rgba(255, 140, 0, 0.5); outline-offset: -1px; } a { color: #FFD700; text-decoration: none; transition: color 0.3s ease; } a:hover { color: #FFDAB9; } .button { display: inline-block; background-color: #E55B00; color: #FFFFFF; padding: 12px 24px; border-radius: 5px; cursor: pointer; text-decoration: none; font-family: 'Cinzel', serif; font-weight: 600; transition: all 0.3s ease; border: 1px solid transparent; } .button:hover { background-color: #FF8C00; box-shadow: 0 0 15px rgba(255, 140, 0, 0.5); transform: translateY(-2px); } pre { background-color: rgba(45, 35, 25, 0.95); padding: 15px; border-radius: 5px; overflow-x: auto; border: 1px solid rgba(255, 140, 0, 0.2); outline: 1px solid rgba(255, 140, 0, 0.5); outline-offset: -1px; } code { font-family: 'Courier New', monospace; color: #F5EFE6; white-space: pre; } .section-container { margin: 40px 0; } h2 { font-size: 26px; color: #FFA500; text-shadow: 0 0 10px rgba(255, 140, 0, 0.5); border-bottom: 1px solid rgba(255, 140, 0, 0.2); padding-bottom: 10px; margin-bottom: 20px; } .info-card { background: rgba(45, 35, 25, 0.95); border: 1px solid rgba(255, 140, 0, 0.2); border-radius: 8px; overflow: hidden; margin-bottom: 25px; } .info-header { background: rgba(255, 140, 0, 0.1); padding: 20px; border-bottom: 1px solid rgba(255, 140, 0, 0.2); } .info-header h3 { color: #FFA500; margin: 0 0 10px 0; font-size: 22px; text-shadow: 0 0 5px rgba(255, 140, 0, 0.3); } .model-tags { display: flex; gap: 8px; flex-wrap: wrap; } .model-tag { background: rgba(218, 165, 32, 0.15); color: #FFD700; padding: 4px 8px; border-radius: 4px; font-size: 12px; border: 1px solid rgba(218, 165, 32, 0.3); font-family: 'Quicksand', sans-serif; } .card-content { padding: 20px; line-height: 1.7; } .card-content p, .card-content li { margin-bottom: 1em; } .card-content p:last-child, .card-content li:last-child { margin-bottom: 0; } .card-content ul { list-style: none; padding-left: 20px; } .card-content li::before { content: '✦'; color: #FFD700; font-weight: bold; display: inline-block; width: 1em; margin-left: -1.2em; font-size: 1.2em; line-height: 1; } .card-content strong { color: #FFD700; font-weight: 600; } .config-container { background: rgba(45, 35, 25, 0.95); border: 1px solid rgba(255, 140, 0, 0.2); border-radius: 8px; overflow: hidden; } .config-header { background: rgba(255, 140, 0, 0.1); padding: 15px 20px; border-bottom: 1px solid rgba(255, 140, 0, 0.2); } .config-header h3 { margin: 0; color: #FFA500; font-size: 22px; } .config-content { padding: 20px; display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 20px; } .config-item { display: flex; flex-direction: column; gap: 5px; } .config-label { color: #FFD700; font-size: 14px; font-weight: 500; font-family: 'Quicksand', sans-serif; } .config-value { color: #F5EFE6; font-family: 'Courier New', monospace; font-size: 18px; font-weight: bold; } .link-arrow { display: inline-block; transition: transform 0.3s ease; } a:hover .link-arrow { transform: translateX(3px); } .support-section { text-align: center; margin-top: 40px; background: rgba(45, 35, 25, 0.95); border: 1px solid rgba(255, 140, 0, 0.2); border-radius: 8px; padding: 20px; } .support-section p { margin-bottom: 15px; font-size: 1.1em; margin-top: 0; } summary { cursor: pointer; list-style: none; outline: none; display: flex; align-items: flex-start; } summary::-webkit-details-marker { display: none; } summary::before { content: '▶'; font-size: 1.2em; color: #FFA500; /* Match h2 color */ margin-right: 15px; padding-top: 5px; /* Adjust vertical alignment with h2 text */ transition: transform 0.2s ease; flex-shrink: 0; /* Prevent the arrow from shrinking */ } details[open] > summary::before { transform: rotate(90deg); } summary > h2 { flex-grow: 1; } .format-list { margin: 1.5em 0; } .format-list dt { color: #FFA500; font-family: 'Cinzel', serif; font-weight: 600; font-size: 1.3em; text-shadow: 0 0 8px rgba(255, 140, 0, 0.5); margin-bottom: 0.6em; } .format-list dd { margin-left: 0; margin-bottom: 1.5em; background-color: rgba(28, 22, 18, 0.95); padding: 12px 15px; border-radius: 6px; border: 1px solid rgba(255, 140, 0, 0.2); border-left: 4px solid #FFA500; } .format-list dd:last-of-type { margin-bottom: 0; }     Ministral-3-8B-Animus-V12.0-GGUF     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 Tekken instruction template. Ensure your client is configured correctly to avoid degraded performance. Human-Readable Format: [SYSTEM_PROMPT]System Message[/SYSTEM_PROMPT][INST]User Message[/INST]Assistant Message Jinja Template: {{- bos_token }}{%- set default_system_message = 'You are Ministral-3-8B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYou power an AI assistant called Le Chat.\\nYour knowledge base was last updated on 2023-10-01.\\nThe current date is {today}.\\n\\nWhen you\\'re not sure about some information or when the user\\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\\'t have the information and avoid making up anything.\\nIf the user\\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\").\\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. \"yesterday\" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\\nNext sections describe the capabilities that you have.\\n\\n# WEB BROWSING INSTRUCTIONS\\n\\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\\n\\n# MULTI-MODAL INSTRUCTIONS\\n\\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\\nYou cannot read nor transcribe audio files or videos.\\n\\n# TOOL CALLING INSTRUCTIONS\\n\\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\\n\\n1. When the request requires up-to-date information.\\n2. When the request requires specific data that you do not have in your knowledge base.\\n3. When the request involves actions that you cannot perform without tools.\\n\\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}{%- if messages[0]['role'] == 'system' %}{{- '[SYSTEM_PROMPT]' -}}{%- if messages[0]['content'] is string %}{{- messages[0]['content'] -}}{%- else %}{%- for block in messages[0]['content'] %}{%- if block['type'] == 'text' %}{{- block['text'] }}{%- else %}{{- raise_exception('Only text chunks are supported in system message contents.') }}{%- endif %}{%- endfor %}{%- endif %}{{- '[/SYSTEM_PROMPT]' -}}{%- set loop_messages = messages[1:] %}{%- else %}{%- set loop_messages = messages %}{%- if default_system_message != '' %}{{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}{%- endif %}{%- endif %}{%- set tools_definition = '' %}{%- set has_tools = false %}{%- if tools is defined and tools is not none and tools|length > 0 %}{%- set has_tools = true %}{%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}{{- tools_definition }}{%- endif %}{%- set ns = namespace(index=0) %}{%- for message in loop_messages %}{%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}{%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}{{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}{%- endif %}{%- set ns.index = ns.index + 1 %}{%- endif %}{%- endfor %}{%- for message in loop_messages %}{%- if message['role'] == 'user' %}{%- if message['content'] is string %}{{- '[INST]' + message['content'] + '[/INST]' }}{%- elif message['content'] | length > 0 %}{{- '[INST]' }}{%- if message['content'] | length == 2 %}{%- set blocks = message['content'] | sort(attribute='type') %}{%- else %}{%- set blocks = message['content'] %}{%- endif %}{%- for block in blocks %}{%- if block['type'] == 'text' %}{{- block['text'] }}{%- elif block['type'] in ['image', 'image_url'] %}{{- '[IMG]' }}{%- else %}{{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}{%- endif %}{%- endfor %}{{- '[/INST]' }}{%- else %}{{- raise_exception('User message must have a string or a list of chunks in content') }}{%- endif %}{%- elif message['role'] == 'assistant' %}{%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}{{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}{%- endif %}{%- if message['content'] is string %}{{- message['content'] }}{%- elif message['content'] | length > 0 %}{%- for block in message['content'] %}{%- if block['type'] == 'text' %}{{- block['text'] }}{%- else %}{{- raise_exception('Only text chunks are supported in assistant message contents.') }}{%- endif %}{%- endfor %}{%- endif %}{%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}{%- for tool in message['tool_calls'] %}{%- set arguments = tool['function']['arguments'] %}{%- if arguments is not string %}{%- set arguments = arguments|tojson|safe %}{%- elif arguments == '' %}{%- set arguments = '{}' %}{%- endif %}{{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}{%- endfor %}{%- endif %}{{- eos_token }}{%- elif message['role'] == 'tool' %}{{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}{%- else %}{{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role']) }}{%- endif %}{%- endfor %}       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:  Temp: 1.0 Min P: 0.035 Dry: 0.8 , 1.75, 4         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 12.0, in the Animus series. V12.0 is a direct fine-tune of mistralai/Ministral-3-8B-Instruct-2512-BF16. V12.0's strength comes from a novel dataset designed to teach the model the why behind the lore, not just the what. The training data is a mix of:  A 3,000-example Q&A dataset: This data is framed as an in-character study session, like a student at Jade Mountain Academy learning about the history, relationships, and politics of Pyrrhia's tribes. This provides a deep, contextual understanding of the universe. A 3,000-example uncensored roleplay dataset: The same high-quality, mature roleplay scenarios used in previous versions, ensuring the model maintains its engaging and dynamic narrative capabilities.  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   V12.0 Training Process   V12.0 marks a shift from model merging to a focused, direct fine-tuning approach. This allows for greater control over the final model's characteristics.  Base Model: mistralai/Ministral-3-8B-Instruct-2512-BF16 Hardware: 3x NVIDIA RTX 3090 Method: Local Training Epochs: 3 Rank: 128      Training Dataset   The V12.0 dataset consists of 6,000 high-quality examples, a combination of two distinct types:  In-Character Q&A (3,000 examples): This new dataset simulates a student at Jade Mountain Academy studying the world's lore. It's composed of roleplay-style questions and answers covering tribe history, family dynamics, and political relationships. This method builds a foundational, interconnected understanding of the lore. Uncensored Roleplay (3,000 examples): This is the same mature, canon-centric dataset refined for previous versions. It explores pivotal \"what-if\" scenarios from the books using only canon characters, ensuring the model can handle complex and dramatic narratives.  Both datasets underwent a rigorous cleaning process to remove formatting artifacts, such as **scene transitions**, 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 and will likely be poor. Versatility: While it appears to be only a Wings of Fire tuned model, users have reported it is very capable of performing normal roleplay with other settings and characters. The model may \"hallucinate\" or generate plausible but non-canonical information, especially when pushed outside the established \"what-if\" scenarios. Content: The training data includes mature and darker themes from the Wings of Fire series, such as conflict, character death, and moral ambiguity. The model is capable of generating content reflecting these themes. As always, it is up to the user what they do with it. Formatting: Training data was cleaned to remove narrative artifacts like **scene transitions**. The model should now produce cleaner prose. Safety: This model has not undergone additional safety alignment beyond what was included in its base model. Standard responsible AI practices should be followed.          Acknowledgements    Credit to Mistral AI for the powerful Ministral-3-8B-Instruct-2512-BF16 model. Credit to Google for the Gemini Pro model, used in dataset generation.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\ntags:\n- finetune\n- roleplay\n- chat\n- wings-of-fire\n- nsfw\n- not-for-all-audiences\nbase_model:\n- Darkhn/Ministral-3-8B-Animus-V12.0\n---\n\n<style>\nbody {\n  font-family: 'Quicksand', sans-serif;\n  background: linear-gradient(135deg, #4a1e00 0%, #1c0a00 100%);\n  color: #F5EFE6;\n  margin: 0;\n  padding: 0;\n  font-size: 16px;\n}\n\nh1, h2, h3, h4, summary {\n    font-family: 'Cinzel', serif;\n}\n\n.container {\n  margin: 20px auto;\n  max-width: 900px;\n  background-color: rgba(28, 22, 18, 0.95);\n  padding: 30px;\n  border-radius: 12px;\n  box-shadow: 0 4px 20px rgba(255, 140, 0, 0.15);\n  border: 1px solid rgba(255, 140, 0, 0.2);\n  outline: 1px solid rgba(255, 140, 0, 0.5);\n  outline-offset: -1px;\n  position: relative;\n}\n\n.container::before {\n  content: '';\n  position: absolute;\n  top: -1px;\n  left: -1px;\n  right: -1px;\n  bottom: -1px;\n  border: 1px solid rgba(255, 165, 0, 0.98);\n  border-radius: 12px;\n  pointer-events: none;\n  animation: borderGlow 2.5s ease-in-out infinite;\n}\n\n@keyframes borderGlow {\n  0% {\n    box-shadow: 0 0 5px rgba(255, 165, 0, 0.98);\n  }\n  50% {\n    box-shadow: 0 0 12px rgba(255, 165, 0, 0.98);\n  }\n  100% {\n    box-shadow: 0 0 5px rgba(255, 165, 0, 0.98);\n  }\n}\n\n.header h1 {\n  font-size: 32px;\n  color: #FFA500;\n  margin: 0 0 20px 0;\n  text-align: center;\n  text-shadow: 0 0 12px rgba(255, 100, 0, 0.6);\n}\n\n.info img {\n  width: 100%;\n  max-width: 700px;\n  display: block;\n  margin: 0 auto 25px auto;\n  border-radius: 10px;\n  box-shadow: 0 0 20px rgba(255, 140, 0, 0.25);\n  border: 1px solid rgba(255, 140, 0, 0.2);\n  outline: 1px solid rgba(255, 140, 0, 0.5);\n  outline-offset: -1px;\n}\n\na {\n  color: #FFD700;\n  text-decoration: none;\n  transition: color 0.3s ease;\n}\n\na:hover {\n  color: #FFDAB9;\n}\n\n.button {\n  display: inline-block;\n  background-color: #E55B00;\n  color: #FFFFFF;\n  padding: 12px 24px;\n  border-radius: 5px;\n  cursor: pointer;\n  text-decoration: none;\n  font-family: 'Cinzel', serif;\n  font-weight: 600;\n  transition: all 0.3s ease;\n  border: 1px solid transparent;\n}\n\n.button:hover {\n  background-color: #FF8C00;\n  box-shadow: 0 0 15px rgba(255, 140, 0, 0.5);\n  transform: translateY(-2px);\n}\n\npre {\n  background-color: rgba(45, 35, 25, 0.95);\n  padding: 15px;\n  border-radius: 5px;\n  overflow-x: auto;\n  border: 1px solid rgba(255, 140, 0, 0.2);\n  outline: 1px solid rgba(255, 140, 0, 0.5);\n  outline-offset: -1px;\n}\n\ncode {\n  font-family: 'Courier New', monospace;\n  color: #F5EFE6;\n  white-space: pre; \n}\n\n.section-container {\n  margin: 40px 0;\n}\n\nh2 {\n    font-size: 26px;\n    color: #FFA500;\n    text-shadow: 0 0 10px rgba(255, 140, 0, 0.5);\n    border-bottom: 1px solid rgba(255, 140, 0, 0.2);\n    padding-bottom: 10px;\n    margin-bottom: 20px;\n}\n\n.info-card {\n  background: rgba(45, 35, 25, 0.95);\n  border: 1px solid rgba(255, 140, 0, 0.2);\n  border-radius: 8px;\n  overflow: hidden;\n  margin-bottom: 25px;\n}\n\n.info-header {\n  background: rgba(255, 140, 0, 0.1);\n  padding: 20px;\n  border-bottom: 1px solid rgba(255, 140, 0, 0.2);\n}\n\n.info-header h3 {\n  color: #FFA500;\n  margin: 0 0 10px 0;\n  font-size: 22px;\n  text-shadow: 0 0 5px rgba(255, 140, 0, 0.3);\n}\n\n.model-tags {\n  display: flex;\n  gap: 8px;\n  flex-wrap: wrap;\n}\n\n.model-tag {\n  background: rgba(218, 165, 32, 0.15);\n  color: #FFD700;\n  padding: 4px 8px;\n  border-radius: 4px;\n  font-size: 12px;\n  border: 1px solid rgba(218, 165, 32, 0.3);\n  font-family: 'Quicksand', sans-serif;\n}\n\n.card-content {\n  padding: 20px;\n  line-height: 1.7;\n}\n\n.card-content p, .card-content li {\n    margin-bottom: 1em;\n}\n\n.card-content p:last-child, .card-content li:last-child {\n    margin-bottom: 0;\n}\n\n.card-content ul {\n    list-style: none;\n    padding-left: 20px;\n}\n\n.card-content li::before {\n    content: '✦';\n    color: #FFD700;\n    font-weight: bold;\n    display: inline-block;\n    width: 1em;\n    margin-left: -1.2em;\n    font-size: 1.2em;\n    line-height: 1;\n}\n\n.card-content strong {\n    color: #FFD700;\n    font-weight: 600;\n}\n\n.config-container {\n  background: rgba(45, 35, 25, 0.95);\n  border: 1px solid rgba(255, 140, 0, 0.2);\n  border-radius: 8px;\n  overflow: hidden;\n}\n\n.config-header {\n  background: rgba(255, 140, 0, 0.1);\n  padding: 15px 20px;\n  border-bottom: 1px solid rgba(255, 140, 0, 0.2);\n}\n\n.config-header h3 {\n    margin: 0;\n    color: #FFA500;\n    font-size: 22px;\n}\n\n.config-content {\n  padding: 20px;\n  display: grid;\n  grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));\n  gap: 20px;\n}\n\n.config-item {\n  display: flex;\n  flex-direction: column;\n  gap: 5px;\n}\n\n.config-label {\n  color: #FFD700;\n  font-size: 14px;\n  font-weight: 500;\n  font-family: 'Quicksand', sans-serif;\n}\n\n.config-value {\n  color: #F5EFE6;\n  font-family: 'Courier New', monospace;\n  font-size: 18px;\n  font-weight: bold;\n}\n\n.link-arrow {\n  display: inline-block;\n  transition: transform 0.3s ease;\n}\n\na:hover .link-arrow {\n  transform: translateX(3px);\n}\n\n.support-section {\n    text-align: center;\n    margin-top: 40px;\n    background: rgba(45, 35, 25, 0.95);\n    border: 1px solid rgba(255, 140, 0, 0.2);\n    border-radius: 8px;\n    padding: 20px;\n}\n\n.support-section p {\n    margin-bottom: 15px;\n    font-size: 1.1em;\n    margin-top: 0;\n}\n\nsummary {\n    cursor: pointer;\n    list-style: none;\n    outline: none;\n    display: flex;\n    align-items: flex-start;\n}\nsummary::-webkit-details-marker {\n    display: none;\n}\nsummary::before {\n    content: '▶';\n    font-size: 1.2em;\n    color: #FFA500; /* Match h2 color */\n    margin-right: 15px;\n    padding-top: 5px; /* Adjust vertical alignment with h2 text */\n    transition: transform 0.2s ease;\n    flex-shrink: 0; /* Prevent the arrow from shrinking */\n}\ndetails[open] > summary::before {\n    transform: rotate(90deg);\n}\nsummary > h2 {\n    flex-grow: 1;\n}\n\n.format-list {\n  margin: 1.5em 0;\n}\n\n.format-list dt {\n  color: #FFA500;\n  font-family: 'Cinzel', serif;\n  font-weight: 600;\n  font-size: 1.3em;\n  text-shadow: 0 0 8px rgba(255, 140, 0, 0.5);\n  margin-bottom: 0.6em;\n}\n\n.format-list dd {\n  margin-left: 0;\n  margin-bottom: 1.5em;\n  background-color: rgba(28, 22, 18, 0.95);\n  padding: 12px 15px;\n  border-radius: 6px;\n  border: 1px solid rgba(255, 140, 0, 0.2);\n  border-left: 4px solid #FFA500;\n}\n\n.format-list dd:last-of-type {\n  margin-bottom: 0;\n}\n</style>\n<div class=\"container\">\n<link href=\"https://fonts.googleapis.com/css2?family=Cinzel:wght@400;500;600&family=Quicksand:wght@400;500&display=swap\" rel=\"stylesheet\">\n<div class=\"header\">\n  <h1>Ministral-3-8B-Animus-V12.0-GGUF</h1>\n</div>\n<div class=\"info\">\n  <img src=\"image.png\" alt=\"Wings_of_Fire\" width=\"700\">\n\n  <div class=\"support-section\">\n    <p><strong>Send me your support to help me feed the data beast! also taking comissions for universe specific models</strong></p>\n    <a href=\"https://ko-fi.com/som1tokmynam\" target=\"_blank\" class=\"button\">\n      Support on Ko-fi\n    </a>\n  </div>\n\n<div class=\"section-container\">\n  <details open>\n    <summary><h2>Important: Chat Template</h2></summary>\n    <div class=\"info-card\">\n      <div class=\"card-content\">\n        <p>This model uses the <strong>Mistral V7 Tekken</strong> instruction template. Ensure your client is configured correctly to avoid degraded performance.</p>\n        <p><strong>Human-Readable Format:</strong></p>\n        <p><code>[SYSTEM_PROMPT]System Message[/SYSTEM_PROMPT][INST]User Message[/INST]Assistant Message</s></code></p>\n        <p><strong>Jinja Template:</strong></p>\n        <pre><code>{{- bos_token }}{%- set default_system_message = 'You are Ministral-3-8B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYou power an AI assistant called Le Chat.\\nYour knowledge base was last updated on 2023-10-01.\\nThe current date is {today}.\\n\\nWhen you\\'re not sure about some information or when the user\\'s request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don\\'t have the information and avoid making up anything.\\nIf the user\\'s question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\").\\nYou are always very attentive to dates, in particular you try to resolve dates (e.g. \"yesterday\" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.\\nYou follow these instructions in all languages, and always respond to the user in the language they use or request.\\nNext sections describe the capabilities that you have.\\n\\n# WEB BROWSING INSTRUCTIONS\\n\\nYou cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.\\n\\n# MULTI-MODAL INSTRUCTIONS\\n\\nYou have the ability to read images, but you cannot generate images. You also cannot transcribe audio files or videos.\\nYou cannot read nor transcribe audio files or videos.\\n\\n# TOOL CALLING INSTRUCTIONS\\n\\nYou may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:\\n\\n1. When the request requires up-to-date information.\\n2. When the request requires specific data that you do not have in your knowledge base.\\n3. When the request involves actions that you cannot perform without tools.\\n\\nAlways prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.' %}{%- if messages[0]['role'] == 'system' %}{{- '[SYSTEM_PROMPT]' -}}{%- if messages[0]['content'] is string %}{{- messages[0]['content'] -}}{%- else %}{%- for block in messages[0]['content'] %}{%- if block['type'] == 'text' %}{{- block['text'] }}{%- else %}{{- raise_exception('Only text chunks are supported in system message contents.') }}{%- endif %}{%- endfor %}{%- endif %}{{- '[/SYSTEM_PROMPT]' -}}{%- set loop_messages = messages[1:] %}{%- else %}{%- set loop_messages = messages %}{%- if default_system_message != '' %}{{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}{%- endif %}{%- endif %}{%- set tools_definition = '' %}{%- set has_tools = false %}{%- if tools is defined and tools is not none and tools|length > 0 %}{%- set has_tools = true %}{%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}{{- tools_definition }}{%- endif %}{%- set ns = namespace(index=0) %}{%- for message in loop_messages %}{%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}{%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}{{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}{%- endif %}{%- set ns.index = ns.index + 1 %}{%- endif %}{%- endfor %}{%- for message in loop_messages %}{%- if message['role'] == 'user' %}{%- if message['content'] is string %}{{- '[INST]' + message['content'] + '[/INST]' }}{%- elif message['content'] | length > 0 %}{{- '[INST]' }}{%- if message['content'] | length == 2 %}{%- set blocks = message['content'] | sort(attribute='type') %}{%- else %}{%- set blocks = message['content'] %}{%- endif %}{%- for block in blocks %}{%- if block['type'] == 'text' %}{{- block['text'] }}{%- elif block['type'] in ['image', 'image_url'] %}{{- '[IMG]' }}{%- else %}{{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}{%- endif %}{%- endfor %}{{- '[/INST]' }}{%- else %}{{- raise_exception('User message must have a string or a list of chunks in content') }}{%- endif %}{%- elif message['role'] == 'assistant' %}{%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}{{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}{%- endif %}{%- if message['content'] is string %}{{- message['content'] }}{%- elif message['content'] | length > 0 %}{%- for block in message['content'] %}{%- if block['type'] == 'text' %}{{- block['text'] }}{%- else %}{{- raise_exception('Only text chunks are supported in assistant message contents.') }}{%- endif %}{%- endfor %}{%- endif %}{%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}{%- for tool in message['tool_calls'] %}{%- set arguments = tool['function']['arguments'] %}{%- if arguments is not string %}{%- set arguments = arguments|tojson|safe %}{%- elif arguments == '' %}{%- set arguments = '{}' %}{%- endif %}{{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}{%- endfor %}{%- endif %}{{- eos_token }}{%- elif message['role'] == 'tool' %}{{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}{%- else %}{{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role']) }}{%- endif %}{%- endfor %}</code></pre>\n      </div>\n    </div>\n  </details>\n</div>\n\n  <div class=\"section-container\">\n    <details>\n      <summary><h2>Character Card & Lore Book</h2></summary>\n      <div class=\"info-card\">\n        <div class=\"card-content\">\n          <p>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.</p>\n          <a href=\"https://huggingface.co/Darkhn/Sampler_settings_and_system_prompt/tree/main/character_card\" target=\"_blank\" class=\"button\">\n            Download Files <span class=\"link-arrow\">→</span>\n          </a>\n        </div>\n      </div>\n    </details>\n  </div>\n\n  <div class=\"section-container\">\n    <details>\n      <summary><h2>Sampler Presets</h2></summary>\n      <div class=\"info-card\">\n        <div class=\"card-content\">\n          <p>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.</p>\n          <p>Simply download the <code>.json</code> file below and import it into SillyTavern's sampler presets menu.</p>\n          <a href=\"https://huggingface.co/Darkhn/Sampler_settings_and_system_prompt/raw/main/Mistral_V7_Tekken_SillyTavern_settings.json\" target=\"_blank\" class=\"button\">\n            Download SillyTavern Presets <span class=\"link-arrow\">→</span>\n          </a>\n          <p><li>For those that dont use silly tavern, Samplers settings are:</li></p>\n          <ul>\n              <p><strong>Temp:</strong> 1.0</p>\n              <p><strong>Min P:</strong> 0.035</p>\n              <p><strong>Dry:</strong> 0.8 , 1.75, 4</p>\n          </ul>\n        </div>\n      </div>\n    </details>\n  </div>\n  \n  <div class=\"section-container\">\n    <details open>\n        <summary>\n            <h2>Roleplay Format Guide</h2>\n        </summary>\n        <div class=\"info-card\">\n            <div class=\"card-content\">\n                <p>For the best results, use this structured format. This helps the AI clearly distinguish between actions, inner thoughts, and dialogue.</p>\n                <dl class=\"format-list\">\n                    <dt>Actions / Descriptions</dt>\n                    <dd><code>*He walked across the room and stared out the window.*</code></dd>\n                    <dt>Inner Thoughts</dt>\n                    <dd><code>*-I wonder what she's thinking.-*</code></dd>\n                    <dt>Dialogue</dt>\n                    <dd><code>Alex (Curious): \"What do you see out there?\"</code></dd>\n                </dl>\n                <p>Standard novel-style formatting is also understood, but this structured format is preferred for clarity.</p>\n            </div>\n        </div>\n    </details>\n  </div>\n\n  <div class=\"section-container\">\n    <details>\n      <summary><h2>Roleplay Example</h2></summary>\n      <div class=\"info-card\">\n        <div class=\"card-content\">\n          <p>Click the button below to view a full, unedited chatlog demonstrating the model's narrative style and character portrayal.</p>\n          <a href=\"https://huggingface.co/Darkhn/Sampler_settings_and_system_prompt/blob/main/chat_logs/chatlog_mistral_large.png\" target=\"_blank\" class=\"button\">\n            View Chatlog Example <span class=\"link-arrow\">→</span>\n          </a>\n        </div>\n      </div>\n    </details>\n  </div>\n\n  <div class=\"section-container\">\n    <details open>\n      <summary><h2>Model Description</h2></summary>\n      <div class=\"info-card\">\n        <div class=\"card-content\">\n          <p>This is <strong>Version 12.0</strong>, in the Animus series. V12.0 is a direct fine-tune of <strong>mistralai/Ministral-3-8B-Instruct-2512-BF16</strong>.</p>\n\t\t  <p>V12.0's strength comes from a novel dataset designed to teach the model the <em>why</em> behind the lore, not just the <em>what</em>. The training data is a mix of:</p>\n            <ul>\n                <li><strong>A 3,000-example Q&A dataset:</strong> This data is framed as an in-character study session, like a student at Jade Mountain Academy learning about the history, relationships, and politics of Pyrrhia's tribes. This provides a deep, contextual understanding of the universe.</li>\n                <li><strong>A 3,000-example uncensored roleplay dataset:</strong> The same high-quality, mature roleplay scenarios used in previous versions, ensuring the model maintains its engaging and dynamic narrative capabilities.</li>\n            </ul>\n          <p>The result is a model with <strong>exceptionally strong prose and a deep grasp of in-universe lore</strong>, making for a highly immersive and accurate roleplaying experience.</p>\n          <p>Note for roleplay, it follows system prompt and first message, meaning if the first assistant message is short, the following messages will be short.</p>\n        </div>\n      </div>\n    </details>\n  </div>\n  \n  <div class=\"section-container\">\n    <details open>\n      <summary><h2>Training Details</h2></summary>\n      <div class=\"info-card\">\n          <div class=\"info-header\">\n              <h3>V12.0 Training Process</h3>\n          </div>\n          <div class=\"card-content\">\n              <p>V12.0 marks a shift from model merging to a focused, direct fine-tuning approach. This allows for greater control over the final model's characteristics.</p>\n              <ul>\n                  <li><strong>Base Model:</strong> mistralai/Ministral-3-8B-Instruct-2512-BF16</li>\n                  <li><strong>Hardware:</strong> 3x NVIDIA RTX 3090</li>\n                  <li><strong>Method:</strong> Local Training</li>\n                  <li><strong>Epochs:</strong> 3</li>\n                  <li><strong>Rank:</strong> 128</li>\n              </ul>\n          </div>\n      </div>\n      <div class=\"info-card\">\n          <div class=\"info-header\">\n              <h3>Training Dataset</h3>\n          </div>\n          <div class=\"card-content\">\n              <p>The V12.0 dataset consists of <strong>6,000 high-quality examples</strong>, a combination of two distinct types:</p>\n              <ul>\n                  <li><strong>In-Character Q&A (3,000 examples):</strong> This new dataset simulates a student at Jade Mountain Academy studying the world's lore. It's composed of roleplay-style questions and answers covering tribe history, family dynamics, and political relationships. This method builds a foundational, interconnected understanding of the lore.</li>\n                  <li><strong>Uncensored Roleplay (3,000 examples):</strong> This is the same mature, canon-centric dataset refined for previous versions. It explores pivotal \"what-if\" scenarios from the books using only canon characters, ensuring the model can handle complex and dramatic narratives.</li>\n              </ul>\n              <p>Both datasets underwent a rigorous cleaning process to remove formatting artifacts, such as <code>**scene transitions**</code>, resulting in a cleaner and more natural narrative style.</p>\n          </div>\n      </div>\n    </details>\n  </div>\n  \n  <div class=\"section-container\">\n    <details>\n      <summary><h2>Intended Use & Limitations</h2></summary>\n      <div class=\"info-card\">\n          <div class=\"card-content\">\n              <ul>\n                  <li><strong>Intended Use:</strong> The primary purpose of this model is for creative and roleplaying within the <em>Wings of Fire</em> universe. However, user feedback indicates it is also highly effective for general-purpose roleplaying.</li>\n                  <li><strong>Limitations & Quirks:</strong>\n                      <ul>\n                          <li>Performance on tasks outside of its training domain (general knowledge, coding, etc.) is not guaranteed and will likely be poor.</li>\n                          <li><strong>Versatility:</strong> While it appears to be only a <em>Wings of Fire</em> tuned model, users have reported it is very capable of performing normal roleplay with other settings and characters.</li>\n                          <li>The model may \"hallucinate\" or generate plausible but non-canonical information, especially when pushed outside the established \"what-if\" scenarios.</li>\n                          <li><strong>Content:</strong> The training data includes mature and darker themes from the <em>Wings of Fire</em> series, such as conflict, character death, and moral ambiguity. The model is capable of generating content reflecting these themes. As always, it is up to the user what they do with it.</li>\n                          <li><strong>Formatting:</strong> Training data was cleaned to remove narrative artifacts like <code>**scene transitions**</code>. The model should now produce cleaner prose.</li>\n                          <li><strong>Safety:</strong> This model has not undergone additional safety alignment beyond what was included in its base model. Standard responsible AI practices should be followed.</li>\n                      </ul>\n                  </li>\n              </ul>\n          </div>\n      </div>\n    </details>\n  </div>\n\n  <div class=\"section-container\">\n    <details>\n      <summary><h2>Acknowledgements</h2></summary>\n      <div class=\"info-card\">\n          <div class=\"card-content\">\n              <ul>\n                  <li>Credit to Mistral AI for the powerful Ministral-3-8B-Instruct-2512-BF16 model.</li>\n                  <li>Credit to Google for the Gemini Pro model, used in dataset generation.</li>\n              </ul>\n          </div>\n      </div>\n    </details>\n  </div>\n</div>\n</div>",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "finetune",
    "roleplay",
    "chat",
    "wings-of-fire",
    "nsfw",
    "not-for-all-audiences",
    "base_model:Darkhn/Ministral-3-8B-Animus-V12.0",
    "base_model:quantized:Darkhn/Ministral-3-8B-Animus-V12.0",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 654,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-24T14:53:31.000Z",
  "created_at": "2025-12-15T14:28:08.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69401af853c55cf304111fb9",
  "id": "Darkhn-Quants-2/Ministral-3-8B-Animus-V12.0-GGUF",
  "modelId": "Darkhn-Quants-2/Ministral-3-8B-Animus-V12.0-GGUF",
  "sha": "7084d7620f8e200d8b2e0075c562d2ca7d0eca2f",
  "createdAt": "2025-12-15T14:28:08.000Z",
  "lastModified": "2025-12-24T14:53:31.000Z",
  "author": "Darkhn-Quants-2",
  "downloads": 654,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 10
}