richarderkhov/pygmalionai_-_pygmalion-1.3b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\npygmalion-1.3b - GGUF\n- Model creator: https://huggingface.co/PygmalionAI/\n- Original model: https://huggingface.co/PygmalionAI/pygmalion-1.3b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [pygmalion-1.3b.Q2_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q2_K.gguf) | Q2_K | 0.53GB |\n| [pygmalion-1.3b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_XS.gguf) | IQ3_XS | 0.59GB |\n| [pygmalion-1.3b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_S.gguf) | IQ3_S | 0.61GB |\n| [pygmalion-1.3b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_S.gguf) | Q3_K_S | 0.61GB |\n| [pygmalion-1.3b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ3_M.gguf) | IQ3_M | 0.66GB |\n| [pygmalion-1.3b.Q3_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K.gguf) | Q3_K | 0.71GB |\n| [pygmalion-1.3b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_M.gguf) | Q3_K_M | 0.71GB |\n| [pygmalion-1.3b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q3_K_L.gguf) | Q3_K_L | 0.77GB |\n| [pygmalion-1.3b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ4_XS.gguf) | IQ4_XS | 0.74GB |\n| [pygmalion-1.3b.Q4_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_0.gguf) | Q4_0 | 0.77GB |\n| [pygmalion-1.3b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.IQ4_NL.gguf) | IQ4_NL | 0.78GB |\n| [pygmalion-1.3b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K_S.gguf) | Q4_K_S | 0.78GB |\n| [pygmalion-1.3b.Q4_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K.gguf) | Q4_K | 0.85GB |\n| [pygmalion-1.3b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_K_M.gguf) | Q4_K_M | 0.85GB |\n| [pygmalion-1.3b.Q4_1.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q4_1.gguf) | Q4_1 | 0.85GB |\n| [pygmalion-1.3b.Q5_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_0.gguf) | Q5_0 | 0.92GB |\n| [pygmalion-1.3b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K_S.gguf) | Q5_K_S | 0.92GB |\n| [pygmalion-1.3b.Q5_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K.gguf) | Q5_K | 0.98GB |\n| [pygmalion-1.3b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_K_M.gguf) | Q5_K_M | 0.98GB |\n| [pygmalion-1.3b.Q5_1.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q5_1.gguf) | Q5_1 | 1.0GB |\n| [pygmalion-1.3b.Q6_K.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q6_K.gguf) | Q6_K | 1.08GB |\n| [pygmalion-1.3b.Q8_0.gguf](https://huggingface.co/RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf/blob/main/pygmalion-1.3b.Q8_0.gguf) | Q8_0 | 1.4GB |\n\n\n\n\nOriginal model description:\n---\nlicense: agpl-3.0\nlanguage:\n- en\nthumbnail:\ntags:\n- text generation\n- conversational\ninference: false\n\n---\n\n# Pygmalion 1.3B\n\n## Model description\n\nPymalion 1.3B is a proof-of-concept dialogue model based on EleutherAI's [pythia-1.3b-deduped](https://huggingface.co/EleutherAI/pythia-1.3b-deduped).\n\n**Warning:** This model is **NOT** suitable for use by minors. It **will** output X-rated content under certain circumstances.\n\n## Training data\n\nThe fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations.\n\n## Training procedure\n\nFine-tuning was done using [ColossalAI](https://github.com/hpcaitech/ColossalAI) (specifically, with a slightly modified version of their [OPT fine-tune example](https://github.com/hpcaitech/ColossalAI/blob/78509124d32b63b7fc36f6508e0576a326d51422/examples/language/opt/run_clm.py)) for around 11.4 million tokens over 5440 steps on a single 24GB GPU. The run took just under 21 hours.\n\n## Intended use\n\n### The easy way\n\nWe provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb).\n\n### The manual way\n\nThe model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format:\n\n```\n[CHARACTER]'s Persona: [A few sentences about the character you want the model to play]\n\n[DIALOGUE HISTORY]\nYou: [Your input message here]\n[CHARACTER]:\n```\n\nWhere `[CHARACTER] `is, as you can probably guess, the name of the character you want the model to portray, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like:\n\n```\n[CHARACTER]: [some dialogue here]\nYou: [your response to the dialogue above]\n```\n\nApart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition.\n\n## Known issues\n\n- The model can get stuck repeating certain phrases, or sometimes even entire sentences.\n  - We believe this is due to that behavior being present in the training data itself, and plan to investigate and adjust accordingly for future versions.\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 161,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-05T16:15:07.000Z",
  "created_at": "2024-06-05T14:21:14.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6660745a4c8677d5c3abad74",
  "id": "RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf",
  "modelId": "RichardErkhov/PygmalionAI_-_pygmalion-1.3b-gguf",
  "sha": "3a91067ffa4f0d87d79223ebe1b274b4e9d7c985",
  "createdAt": "2024-06-05T14:21:14.000Z",
  "lastModified": "2024-06-05T16:15:07.000Z",
  "author": "RichardErkhov",
  "downloads": 161,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}