ewof/koishi-7b-qlora-gguf overview

{
  "metadata": {},
  "card_data": {
    "datasets": [
      "ewof/koishi-instruct-metharme"
    ],
    "frontmatter": {
      "datasets": [
        "ewof/koishi-instruct-metharme"
      ]
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ndatasets:\n  - ewof/koishi-instruct-metharme\n---\n\n## GGUF\n\nlittle endian\n\n\n## Training\n\n[axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) was used for training\non a 6x nvidia a40 gpu cluster.\n\nthe a40 GPU cluster has been graciously provided by [Arc Compute](https://www.arccompute.io/).\n\ntrained on koishi commit 6e675d1 for one epoch\n\n## Base Model\n\nrank 16 lora tune of mistralai/Mistral-7B-v0.1 (all modules, merged)\n\n## Prompting\n\nThe current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.\n\nThe `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "mistral",
    "dataset:ewof/koishi-instruct-metharme",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 105,
  "gated": false,
  "private": false,
  "last_modified": "2024-04-09T08:26:04.000Z",
  "created_at": "2023-12-15T23:59:02.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "657ce84617f67d5b8791e40e",
  "id": "ewof/koishi-7b-qlora-gguf",
  "modelId": "ewof/koishi-7b-qlora-gguf",
  "sha": "49ebfcb3f0564519a2b76d90ee74a803e75bf966",
  "createdAt": "2023-12-15T23:59:02.000Z",
  "lastModified": "2024-04-09T08:26:04.000Z",
  "author": "ewof",
  "downloads": 105,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 16
}