lewdiculous/l3-thespice-8b-v0.8.3-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "license": "cc-by-4.0",
    "frontmatter": {
      "license": "cc-by-4.0"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png",
    "summary": "> [!IMPORTANT] > Version 2 files uploaded! GGUF-IQ-Imatrix quants for cgato/L3-TheSpice-8b-v0.8.3. > [!IMPORTANT] > These quants have already been done after the fixes from llama.cpp/pull/6920.  > Use **KoboldCpp version 1.64** or higher. > [!NOTE] > **Prompt formatting...**  > Prompt format is relatively simple, author seems to recommend the **Default** context preset and **Instruct Mode - Disabled**.  > I recommend reading original **model card page information**. !image/png # Original model information by the author: Now not overtrained and with the tokenizer fix to base llama3. Trained for 3 epochs. The latest TheSpice, dipped in Mama Liz's LimaRP Oil. I've focused on making the model more flexible and provide a more unique experience. I'm still working on cleaning up my dataset, but I've shrunken it down a lot to focus on a \"less is more\" approach. This is ultimate a return to form of the way I used to train Thespis, with more of a focus on a small hand edited dataset.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: cc-by-4.0\n---\n\n# #llama-3 #roleplay\n\n> [!IMPORTANT]  \n> Version 2 files uploaded!\n\nGGUF-IQ-Imatrix quants for [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3).\n\n> [!IMPORTANT]  \n> These quants have already been done after the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920). <br>\n> Use **KoboldCpp version 1.64** or higher.\n\n> [!NOTE]\n> **Prompt formatting...** <br>\n> Prompt format is relatively simple, author seems to recommend the **Default** context preset and **Instruct Mode - Disabled**. <br>\n> I recommend reading original [**model card page information**](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3#prompt-format-chat--the-default-ooba-template-and-silly-tavern-template-).\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png)\n\n# Original model information by the author:\n\nNow not overtrained and with the tokenizer fix to base llama3. Trained for 3 epochs.\n\nThe latest TheSpice, dipped in Mama Liz's LimaRP Oil.\nI've focused on making the model more flexible and provide a more unique experience. \nI'm still working on cleaning up my dataset, but I've shrunken it down a lot to focus on a \"less is more\" approach.\nThis is ultimate a return to form of the way I used to train Thespis, with more of a focus on a small hand edited dataset.\n\n\n## Datasets Used\n\n* Capybara\n* Claude Multiround 30k\n* Augmental\n* ToxicQA\n* Yahoo Answers\n* Airoboros 3.1\n* LimaRP\n\n## Features ( Examples from 0.1.1 because I'm too lazy to take new screenshots. Its tested tho. )\n\nNarration\n\nIf you request information on objects or characters in the scene, the model will narrate it to you. Most of the time, without moving the story forward.\n\n# You can look at anything mostly as long as you end it with \"What do I see?\"\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/VREY8QHtH6fCL0fCp8AAC.png)\n\n# You can also request to know what a character is thinking or planning.\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/U3RTAgbaB2m1ygfZGJ-SM.png)\n\n# You can ask for a quick summary on the character as well.\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/uXFd6GhnXS8w_egUEfcAp.png)\n\n# Before continuing the conversation as normal.\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/dYTQUdCshUDtp_BJ20tHy.png)\n\n## Prompt Format: Chat ( The default Ooba template and Silly Tavern Template )\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/59vi4VWP2d0bCbsW2eU8h.png)\n\nIf you're using Ooba in verbose mode as a server, you can check if you're console is logging something that looks like this. \n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/mB3wZqtwN8B45nR7W1fgR.png)\n\n```\n{System Prompt}\n\nUsername: {Input}\nBotName: {Response}\nUsername: {Input}\nBotName: {Response}\n\n```\n## Presets\n\nAll screenshots above were taken with the below SillyTavern Preset.\n## Recommended Silly Tavern Preset -> (Temp: 1.25, MinP: 0.1, RepPen: 1.05)\nThis is a roughly equivalent Kobold Horde Preset.\n## Recommended Kobold Horde Preset -> MinP\n\n\n# Disclaimer\n\nPlease prompt responsibly and take anything outputted by any Language Model with a huge grain of salt. Thanks!",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "license:cc-by-4.0",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 18,
  "downloads": 246,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-15T14:01:40.000Z",
  "created_at": "2024-05-03T12:26:37.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6634d7fd38a2c7fe6be963e7",
  "id": "Lewdiculous/L3-TheSpice-8b-v0.8.3-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/L3-TheSpice-8b-v0.8.3-GGUF-IQ-Imatrix",
  "sha": "376d3d7c11bbc6dff0f31d3a30f1265e3f47fa54",
  "createdAt": "2024-05-03T12:26:37.000Z",
  "lastModified": "2024-05-15T14:01:40.000Z",
  "author": "Lewdiculous",
  "downloads": 246,
  "likes": 18,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 28
}