shoumenchougou/rwkv7-g1d-0.1b-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "frontmatter": {
      "license": "apache-2.0"
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\n---\n\n\n## 1️⃣ What are G0 / G1 / G1a2 / G1b / G1c / G1d ?\n\nThe fields like G0a / G1a / G1a2 in RWKV model names indicate versions of the training data. In terms of data quality, the ranking is:  **G1d > G1c > G1b > G1a2 > G1a > G1 > G0a2 > G0**.\n\nThe RWKV7-G1a model is an advanced version of RWKV7-G1 that was further trained with 1T (1 trillion tokens) of high-quality inference and instruction data. RWKV7-G1a2 was produced by continuing to add more data and training on top of RWKV7-G1a.\n\n>  [!TIP]\n>  More high-quality data will be added later to form the G1b dataset, and RWKV7-G1b series models will also be trained and open-sourced.\n\n## 2️⃣ What is the difference between the RWKV7-G series and the World series?\n\nThe RWKV7-G series supports an inference mode, which can be activated using the following format:\n\n```\nUser: USER_PROMPT\n\nAssistant: <think\n```\n\n## 3️⃣ How to choose the best model?\n\n**Look at the date in the model name** — for the same parameter size, a newer model is better!\n\nFor example, for the same 1.5B model, a G1a2 version released on `251005` will definitely be superior to a G1 version released on `250429`.\n\n> [!WARNING] \n> For the 0.1B and 0.4B models, we recommend using FP16/Q8_0 quantization. Otherwise, the models may fail to complete tasks due to precision loss caused by quantization.**\n \n\n---\n\n\n## 1️⃣ G0/G1/G1a2/G1b/G1c 是什么?\n\nRWKV 模型名称中的 G0a/G1a/G1a2 等字段是训练数据的版本，数据质量排序：**G1d > G1c > G1b > G1a2 > G1a > G1 > G0a2 > G0** 。\n\nRWKV7-G1a 模型是在 RWKV7-G1 模型的基础上继续训练了 1T 优质推理和指令数据的进阶版，RWKV7-G1a2 则是在 RWKV7-G1a 模型的基础上继续添加数据训练，以此类推。\n\n## 2️⃣ RWKV7-G 系列和 World 系列有什么区别？\n\nRWKV7-G 系列模型支持推理模式，可通过以下格式开启推理模式：\n\n```\nUser: USER_PROMPT\n\nAssistant: <think\n```\n\n## 3️⃣ 如何选择最好的模型？\n\n**看模型名称中的日期**，相同的参数，模型越新越好！\n\n比如同样是 1.5B 模型，发布于 `251005` 的 G1a2 版本必定优于 `250429` 的 G1 版本 。\n\n> [!WARNING] \n> 对于 0.1B 和 0.4B 模型，我们建议使用 FP16/Q8_0 量化类型。否则模型可能因量化带来的精度损失而无法完成任务。\n\n\n ",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 163,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-26T09:21:11.000Z",
  "created_at": "2026-02-02T07:08:10.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "69804d5a766edf09745ad85d",
  "id": "shoumenchougou/RWKV7-G1d-0.1B-GGUF",
  "modelId": "shoumenchougou/RWKV7-G1d-0.1B-GGUF",
  "sha": "822c5caa641d836a6b9be891d286734ded490312",
  "createdAt": "2026-02-02T07:08:10.000Z",
  "lastModified": "2026-03-26T09:21:11.000Z",
  "author": "shoumenchougou",
  "downloads": 163,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 7
}