lewdiculous/lemonaderp-4.5.3-gguf-iq-imatrix overview

{
  "metadata": {},
  "card_data": {
    "library_name": "transformers",
    "license": "cc-by-4.0",
    "language": [
      "en"
    ],
    "tags": [
      "gguf",
      "quantized",
      "roleplay",
      "imatrix",
      "mistral",
      "merge"
    ],
    "inference": false,
    "frontmatter": {
      "library_name": "transformers",
      "license": "cc-by-4.0",
      "language": [
        "en"
      ],
      "tags": [
        "gguf",
        "quantized",
        "roleplay",
        "imatrix",
        "mistral",
        "merge"
      ],
      "inference": "false"
    },
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/653a2392341143f7774424d8/MtdRhFSBULJF4Upqch2gA.png",
    "summary": "This repository hosts GGUF-IQ-Imatrix quantizations for KatyTheCutie/LemonadeRP-4.5.3. `` --contextsize 8192 ` **What does \"Imatrix\" mean?** It stands for **Importance Matrix**, a technique used to improve the quality of quantized models. The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse. [[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) For imatrix data generation, kalomaze's groups_merged.txt with added roleplay chats was used, you can find it here. **Steps:** ` Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants) ` **Quants:** `python quantization_options = [ \"Q4_K_M\", \"IQ4_XS\", \"Q5_K_M\", \"Q5_K_S\", \"Q6_K\", \"Q8_0\", \"IQ3_M\", \"IQ3_S\", \"IQ3_XXS\" ] `` If you want anything that's not here or another model, feel free to request. **Original model information:** !image/png Lemonade RP 4.5.3 8192 context length. 7B roleplay focused model, creativity and less cliché is the focus of this merge. SillyTavern settings: !image/png !image/png Models used in merge: Feedback is always greatly appreciated! <3",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: transformers\nlicense: cc-by-4.0\nlanguage:\n- en\ntags:\n- gguf\n- quantized\n- roleplay\n- imatrix\n- mistral\n- merge\ninference: false\n# base_model:\n# - Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context\n# - Epiculous/Mika-7B\n---\n\nThis repository hosts GGUF-IQ-Imatrix quantizations for [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3).\n\n```\n--contextsize 8192\n```\n\n**What does \"Imatrix\" mean?**\n\nIt stands for **Importance Matrix**, a technique used to improve the quality of quantized models.\nThe **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process.\nThe idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse.\n[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)\n\nFor imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt).\n\n**Steps:**\n```\nBase⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)\n```\n**Quants:**\n```python\n    quantization_options = [\n        \"Q4_K_M\", \"IQ4_XS\", \"Q5_K_M\", \"Q5_K_S\", \"Q6_K\",\n        \"Q8_0\", \"IQ3_M\", \"IQ3_S\", \"IQ3_XXS\"\n    ]\n```\n\nIf you want anything that's not here or another model, feel free to request.\n\n**Original model information:**\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/653a2392341143f7774424d8/MtdRhFSBULJF4Upqch2gA.png)\nLemonade RP 4.5.3\n\n8192 context length.\n\n7B roleplay focused model, creativity and less cliché is the focus of this merge.\nSillyTavern settings:\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/653a2392341143f7774424d8/tI2lp0Aeveu6KYBeNFilJ.png)\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/653a2392341143f7774424d8/lGhuJiL5jGRwviNr5GcbN.png)\nModels used in merge:\n- NeverSleep/Noromaid-7B-0.4-DPO\n- cgato/Thespis-7b-v0.5-SFTTest-2Epoch\n- NurtureAI/neural-chat-7b-v3-1-16k\n- cgato/Thespis-CurtainCall-7b-v0.2.2\n- tavtav/eros-7b-test\n\n\nFeedback is always greatly appreciated! <3",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "quantized",
    "roleplay",
    "imatrix",
    "mistral",
    "merge",
    "en",
    "license:cc-by-4.0",
    "region:us"
  ],
  "likes": 14,
  "downloads": 99,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-14T00:03:11.000Z",
  "created_at": "2024-03-13T22:22:09.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "65f227110effe20744e653e1",
  "id": "Lewdiculous/LemonadeRP-4.5.3-GGUF-IQ-Imatrix",
  "modelId": "Lewdiculous/LemonadeRP-4.5.3-GGUF-IQ-Imatrix",
  "sha": "3fde0a6a356e6c08dfe69a029f12290d701dfd74",
  "createdAt": "2024-03-13T22:22:09.000Z",
  "lastModified": "2024-03-14T00:03:11.000Z",
  "author": "Lewdiculous",
  "downloads": 99,
  "likes": 14,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 14
}