README.md

---
license: cc-by-nc-2.0
tags:
- roleplay
- chat
- wings-of-fire
- nsfw
- not-for-all-audiences
base_model: Darkhn/Command-A-111B-Animus-V13.0
base_model_relation: quantized
---

<style>
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;
}

.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;
}
</style>
<div class="container">
<link href="https://fonts.googleapis.com/css2?family=Cinzel:wght@400;500;600&family=Quicksand:wght@400;500&display=swap" rel="stylesheet">
<div class="header">
  <h1>Command-A-111B-Animus-V13.0-EXL3</h1>
</div>
<div class="info">
  <img src="image.png" alt="Wings_of_Fire" width="700">

  <div class="support-section">
    <p><strong>Send me your support to help me feed the data beast! also taking comissions for universe specific models</strong></p>
    <a href="https://ko-fi.com/som1tokmynam" target="_blank" class="button">
      Support on Ko-fi
    </a>
  </div>

<div class="section-container">
  <details open>
    <summary><h2>Chat Template</h2></summary>
    <div class="info-card">
      <div class="card-content">
        <p>This model uses the <strong>Command-A</strong> instruction template. Ensure your client is configured correctly to avoid degraded performance.</p>
        <p><strong>Jinja Template:</strong></p>
        <pre><code>{{ bos_token }}{% if documents %}\n{% set tools = [] %}\n{%- macro document_turn(documents) -%}\n{# format documents into chat turn #}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[\n    {\"tool_call_id\": \"0\", \"tool_name\": \"direct-injected-document\", \"parameters\": {}}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n    {\n        \"tool_call_id\": \"0\",\n        \"results\": {\n{% for doc in documents %}\n            \"{{ loop.index0 }}\": {{doc|tojson}}{% if not loop.last %},\n            {% endif %}\n{% endfor %}\n\n        },\n        \"is_error\": null\n    }\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}\n{%- macro tool_call_id_to_int(messages, tool_call_id) %}\n{%- set counter = namespace(value=0) %}\n{%- set tool_call_id_seen = namespace(value=false) %}\n{%- for msg in messages %}\n    {%- if msg.tool_calls %}\n        {%- for tool_call in msg.tool_calls %}\n            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}\n                {{ counter.value }}\n                {%- set tool_call_id_seen.value = true %}\n            {%- endif %}\n            {%- set counter.value = counter.value + 1 %}\n        {%- endfor %}\n    {%- endif %}\n{%- endfor %}\n{%- endmacro %}\n{%- macro format_tool_message(messages, tool_msg) -%}\n{# format tool message #}\n    {\n        \"tool_call_id\": \"{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}\",\n        \"results\": {\n            \"0\": {{ tool_msg.content|tojson }}\n        },\n        \"is_error\": null\n    }\n{%- endmacro -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n{%- set tool_idx = namespace(value=0) %}\n{%- set tool_ids_seen = namespace(value=[]) %}\n{%- set sent_documents = namespace(value=false) %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\nYou are in contextual safety mode. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n{% if tools or documents %}\n\nYou have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.\n\n## Tool Use\nThink about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.\n\n0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.\n    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.\n    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.\n\nThen carry out your plan by repeatedly executing the following steps.\n1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing \"tool_name\" and \"parameters\" fields.\n    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.\n2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.\n    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its \"tool_call_id\".\n3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.\n    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.\n    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.\n\nYou can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.\n\n4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>\n{% if enable_citations %}\n\n## Grounding\nImportantly, note that \"Reflection\" and \"Response\" above can be grounded.\nGrounding means you associate pieces of texts (called \"spans\") with those specific tool results that support them (called \"sources\"). And you use a pair of tags \"<co>\" and \"</co>\" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as \"{tool_call_id}:[{list of result indices}]\", before they are joined together by \",\". E.g., \"<co>span</co: 0:[1,2],1:[0]>\" means that \"span\" is supported by result 1 and 2 from \"tool_call_id=0\" as well as result 0 from \"tool_call_id=1\".\n{% endif %}\n\n## Available Tools\nHere is the list of tools that you have available to you.\nYou can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.\nEach tool is represented as a JSON object with fields like \"name\", \"description\", \"parameters\" (per JSON Schema), and optionally, \"responses\" (per JSON Schema).\n\n```json\n[\n{% if documents %}\n    {\"name\": \"direct-injected-document\", \"description\": \"This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!\", \"parameters\": {\"type\": \"object\", \"properties\": {}, \"required\": []}, \"responses\": {\"200\": {\"description\": \"Successfully returned a list of chunked text snippets from the directly uploaded documents.\", \"content\": {\"application/json\": {\"schema\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"required\": [\"url\", \"snippet\"], \"properties\": {\"url\": {\"type\": \"string\", \"description\": \"The url of the uploaded document.\"}, \"snippet\": {\"type\": \"string\", \"description\": \"The text snippet for the returned document chunk.\"}}}}}}}}}{%- if tools %},{% endif %}\n\n{% endif %}\n{% for tool in tools %}\n    {\"name\": \"{{ tool['function']['name'] }}\", \"description\": \"{{tool['function']['description']}}\", \"parameters\": {{ tool['function']['parameters']|tojson }}, \"responses\": null}{%- if not loop.last %},{% endif %}\n\n{% endfor %}\n]\n```\n\n{% endif %}\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Command.\n- You are a large language model built by Cohere.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n{%- if developer_preamble %}\n\n\n# Developer Preamble\nThe following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n{{ developer_preamble }}\n{%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages %}\n    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n    {%- elif message.role|lower == 'user' %}\n<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}\n    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[\n    {% for tc in message.tool_calls %}\n    {\"tool_call_id\": \"{{ tool_idx.value }}\", \"tool_name\": \"{{ tc['function']['name'] }}\", \"parameters\": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}\n\n    {% set tool_idx.value = tool_idx.value + 1 %}\n    {% endfor %}\n]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}\n    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[\n{{ format_tool_message(messages, message) }}\n    {%- for msg in messages[loop.index0 + 1:] %}\n        {%- if msg.role|lower == 'tool' %},\n{{ format_tool_message(messages, msg) }}\n            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}\n        {%- else %}\n            {%- break %}\n        {%- endif %}\n    {%- endfor %}\n\n]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>\n    {%- endif %}\n{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>\n{%- else -%}\n{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble\n{% if safety_mode|upper == 'STRICT' -%}\nYou are in strict safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will reject requests to generate content related to violence, hate, misinformation or sex to any amount. You will avoid using profanity. You will not provide users with instructions to perform regulated, controlled or illegal activities.\n{%- else -%}\nYou are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.\n{%- endif %}\n\n\nYour information cutoff date is June 2024.\n\nYou have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.\n\n# Default Preamble\nThe following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.\n- Your name is Command.\n- You are a large language model built by Cohere.\n- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.\n- If the input is ambiguous, ask clarifying follow-up questions.\n- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).\n- Use LaTeX to generate mathematical notation for complex equations.\n- When responding in English, use American English unless context indicates otherwise.\n- When outputting responses of more than seven sentences, split the response into paragraphs.\n- Prefer the active voice.\n- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.\n- Use gender-neutral pronouns for unspecified persons.\n- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.\n- Use the third person when asked to write a summary.\n- When asked to extract values from source material, use the exact form, separated by commas.\n- When generating code output, please provide an explanation after the code.\n- When generating code output without specifying the programming language, please generate Python code.\n- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.\n{%- if developer_preamble %}\n\n\n# Developer Preamble\nThe following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.\n{{ developer_preamble }}\n{%- endif -%}\n<|END_OF_TURN_TOKEN|>\n{%- for message in messages %}\n    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}\n<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n    {%- elif message.role|lower == 'user' %}\n<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>\n    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}\n<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>\n    {%- endif %}\n{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{%- if add_generation_prompt -%}<|START_RESPONSE|>{%- endif %}\n{% endif %}</code></pre>
      </div>
    </div>
  </details>
</div>

<div class="section-container">
  <details>
    <summary><h2>Quantized Models</h2></summary>
    <div class="info-card">
      <div class="card-content">
        <p>The quantized model files are available for download. Click the button below to view the files.</p>
        <a href="https://huggingface.co/Darkhn-Quants-3/Command-A-111B-Animus-V13.0-GGUF" target="_blank" class="button">
          Download GGUF Files <span class="link-arrow">→</span>
        </a>
      </div>
    </div>
  </details>
</div>

<div class="section-container">
    <details>
      <summary><h2>How to Download</h2></summary>
      <div class="info-card">
        <div class="card-content">
          <p>You can download specific model quantizations using the Hugging Face Command Line Interface (CLI). This allows you to select the exact version you need.</p>
          <p><strong>1. Install huggingface-hub with CLI support:</strong></p>
          <pre><code>pip install -U "huggingface_hub[cli]"</code></pre>
          <p><strong>2. Download a specific quant:</strong></p>
          <p>Use the command below, replacing the revision with the desired model version from the repository's branches.</p>
          <pre><code>huggingface-cli download Darkhn-Quants-3/Command-A-111B-Animus-V13.0-EXL3 --revision "6.0bpw_H8" --local-dir ./Command-A-111B-Animus-V13.0-EXL3</code></pre>
        </div>
      </div>
    </details>
  </div>

  <div class="section-container">
    <details>
      <summary><h2>Character Card & Lore Book</h2></summary>
      <div class="info-card">
        <div class="card-content">
          <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>
          <a href="https://huggingface.co/Darkhn/Sampler_settings_and_system_prompt/tree/main/character_card" target="_blank" class="button">
            Download Files <span class="link-arrow">→</span>
          </a>
        </div>
      </div>
    </details>
  </div>

  <div class="section-container">
    <details>
      <summary><h2>Sampler Presets</h2></summary>
      <div class="info-card">
        <div class="card-content">
          <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>
          <p>Simply download the <code>.json</code> file below and import it into SillyTavern's sampler presets menu.</p>
          <a href="https://huggingface.co/Darkhn/Sampler_settings_and_system_prompt/raw/main/Command_A_SillyTavern_settings.json" target="_blank" class="button">
            Download SillyTavern Presets <span class="link-arrow">→</span>
          </a>
          <p><li>For those that dont use silly tavern, Samplers settings are:</li></p>
          <ul>
              <p><strong>Temp:</strong> 0.7</p>
              <p><strong>Min P:</strong> 0.02</p>
          </ul>
        </div>
      </div>
    </details>
  </div>
  
  <div class="section-container">
    <details open>
        <summary>
            <h2>Roleplay Format Guide</h2>
        </summary>
        <div class="info-card">
            <div class="card-content">
                <p>For the best results, use this structured format. This helps the AI clearly distinguish between actions, inner thoughts, and dialogue.</p>
                <dl class="format-list">
                    <dt>Actions / Descriptions</dt>
                    <dd><code>*He walked across the room and stared out the window.*</code></dd>
                    <dt>Inner Thoughts</dt>
                    <dd><code>*-I wonder what she's thinking.-*</code></dd>
                    <dt>Dialogue</dt>
                    <dd><code>Alex (Curious): "What do you see out there?"</code></dd>
                </dl>
                <p>Standard novel-style formatting is also understood, but this structured format is preferred for clarity.</p>
            </div>
        </div>
    </details>
  </div>

  <div class="section-container">
    <details open>
      <summary><h2>Model Description</h2></summary>
      <div class="info-card">
        <div class="card-content">
          <p>This is <strong>Command-A-111B-Animus-V13.0</strong>. This model is a direct fine-tune of <strong>CohereLabs/c4ai-command-a-03-2025</strong>.</p>
		  <p>V13.0'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>
            <ul>
                <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>
                <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>
            </ul>
          <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>
          <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>
        </div>
      </div>
    </details>
  </div>
  
  <div class="section-container">
    <details open>
      <summary><h2>Training Details</h2></summary>
      <div class="info-card">
          <div class="info-header">
              <h3>V13.0 Training Process</h3>
          </div>
          <div class="card-content">
              <p>V13.0 marks a shift to a focused, direct fine-tuning approach using the Command-A architecture.</p>
              <ul>
                  <li><strong>Base Model:</strong> CohereLabs/c4ai-command-a-03-2025</li>
                  <li><strong>Hardware:</strong> NVIDIA B200</li>
                  <li><strong>Epochs:</strong> 3</li>
				  <li><strong>Rank:</strong> 256</li>
				  <li><strong>Training Time:</strong> 22 Hours</li>
              </ul>
          </div>
      </div>
      <div class="info-card">
          <div class="info-header">
              <h3>Training Dataset</h3>
          </div>
          <div class="card-content">
              <p>The V13.0 dataset consists of <strong>6,000 high-quality examples</strong>, a combination of two distinct types:</p>
              <ul>
                  <li><strong>In-Character Q&A (3,000 examples):</strong> This 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.</li>
                  <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>
				  <li>Version 13.0 of the dataset, added a bit more prose from Claude, deepseek and Kimi-K2</li>
              </ul>
          </div>
      </div>
    </details>
  </div>
  
  <div class="section-container">
    <details>
      <summary><h2>Intended Use & Limitations</h2></summary>
      <div class="info-card">
          <div class="card-content">
              <ul>
                  <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>
                  <li><strong>Limitations & Quirks:</strong>
                      <ul>
                          <li>Performance on tasks outside of its training domain (general knowledge, coding, etc.) is not guaranteed.</li>
                          <li><strong>Versatility:</strong> While it appears to be only a <em>Wings of Fire</em> tuned model, it is very capable of performing normal roleplay with other settings and characters.</li>
                          <li>The model may "hallucinate" or generate plausible but non-canonical information, especially when pushed outside established scenarios.</li>
                          <li><strong>Content:</strong> The training data includes mature and darker themes from the <em>Wings of Fire</em> series. Standard responsible AI practices should be followed.</li>
                      </ul>
                  </li>
              </ul>
          </div>
      </div>
    </details>
  </div>

  <div class="section-container">
    <details>
      <summary><h2>Acknowledgements</h2></summary>
      <div class="info-card">
          <div class="card-content">
              <ul>
                  <li>Credit to CohereLabs for the powerful Command-A model.</li>
                  <li>Credit to Google for the Gemini Pro model, used in dataset generation.</li>
				  <li>Credit to Anthropic for sonnet 4.5, used in dataset generation.</li>
				  <li>Credit to Hangzhou DeepSeek Artificial Intelligence for the deepseek model, used in dataset generation.</li>
				  <li>Credit to Moonshot AI for the Kimi K2 model, used in dataset generation.</li>
              </ul>
          </div>
      </div>
    </details>
  </div>
</div>
</div>