GraySoft
Projects Models About FAQ Contact Download guIDE →

duyntnet/pygmalion-2-7b-imatrix-gguf Q2_K_S GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

duyntnet/pygmalion-2-7b-imatrix-gguf overview

Comprehensive model page for duyntnet/pygmalion-2-7b-imatrix-gguf

transformersggufimatrixpygmalion-2-7btext-generationenlicense:otherregion:us
duyntnet/pygmalion-2-7b-imatrix-gguf visual
Downloads
96
Likes
1
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

27 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
pygmalion-2-7b-IQ1_M.gguf GGUF IQ1_M 1.54 GB Download
pygmalion-2-7b-IQ1_S.gguf GGUF IQ1_S 1.42 GB Download
pygmalion-2-7b-IQ2_M.gguf GGUF IQ2_M 2.20 GB Download
pygmalion-2-7b-IQ2_S.gguf GGUF IQ2_S 2.05 GB Download
pygmalion-2-7b-IQ2_XS.gguf GGUF IQ2_XS 1.90 GB Download
pygmalion-2-7b-IQ2_XXS.gguf GGUF IQ2_XXS 1.73 GB Download
pygmalion-2-7b-IQ3_M.gguf GGUF IQ3_M 2.90 GB Download
pygmalion-2-7b-IQ3_S.gguf GGUF IQ3_S 2.75 GB Download
pygmalion-2-7b-IQ3_XS.gguf GGUF IQ3_XS 2.60 GB Download
pygmalion-2-7b-IQ3_XXS.gguf GGUF IQ3_XXS 2.41 GB Download
pygmalion-2-7b-IQ4_NL.gguf GGUF IQ4_NL 3.56 GB Download
pygmalion-2-7b-IQ4_XS.gguf GGUF IQ4_XS 3.37 GB Download
pygmalion-2-7b-Q2_K.gguf GGUF Q2_K 2.36 GB Download
pygmalion-2-7b-Q2_K_S.gguf GGUF Q2_K_S 2.16 GB Download
pygmalion-2-7b-Q3_K_L.gguf GGUF Q3_K_L 3.35 GB Download
pygmalion-2-7b-Q3_K_M.gguf GGUF Q3_K_M 3.07 GB Download
pygmalion-2-7b-Q3_K_S.gguf GGUF Q3_K_S 2.75 GB Download
pygmalion-2-7b-Q4_0.gguf GGUF 3.57 GB Download
pygmalion-2-7b-Q4_1.gguf GGUF 3.95 GB Download
pygmalion-2-7b-Q4_K_M.gguf GGUF Q4_K_M 3.80 GB Download
pygmalion-2-7b-Q4_K_S.gguf GGUF Q4_K_S 3.59 GB Download
pygmalion-2-7b-Q5_0.gguf GGUF 4.34 GB Download
pygmalion-2-7b-Q5_1.gguf GGUF 4.72 GB Download
pygmalion-2-7b-Q5_K_M.gguf GGUF Q5_K_M 4.45 GB Download
pygmalion-2-7b-Q5_K_S.gguf GGUF Q5_K_S 4.33 GB Download
pygmalion-2-7b-Q6_K.gguf GGUF Q6_K 5.15 GB Download
pygmalion-2-7b-Q8_0.gguf GGUF 6.67 GB Download

Model Details Live

Model Slug
duyntnet/pygmalion-2-7b-imatrix-gguf
Author
duyntnet
Pipeline Task
text-generation
Library
transformers
Created
2024-06-13
Last Modified
2024-06-13
Gated
No
Private
No
HF SHA
de0b7f02a14f499fc493fa51326282dd954de5b0
License
other
Language
en
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "other",
    "language": [
      "en"
    ],
    "pipeline_tag": "text-generation",
    "inference": false,
    "tags": [
      "transformers",
      "gguf",
      "imatrix",
      "pygmalion-2-7b"
    ],
    "frontmatter": {
      "license": "other",
      "language": [
        "en"
      ],
      "pipeline_tag": "text-generation",
      "inference": "false",
      "tags": [
        "transformers",
        "gguf",
        "imatrix",
        "pygmalion-2-7b"
      ]
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlanguage:\n- en\npipeline_tag: text-generation\ninference: false\ntags:\n- transformers\n- gguf\n- imatrix\n- pygmalion-2-7b\n---\nQuantizations of https://huggingface.co/PygmalionAI/pygmalion-2-7b\n\n\n# From original readme\n\n## Prompting\n\nThe model 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.\nThe `<|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\nform a conversation history.\n\n### Prompting example\n\nThe system prompt has been designed to allow the model to \"enter\" various modes and dictate the reply length. Here's an example:\n\n```\n<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:\n{{persona}}\n\nYou shall reply to the user while staying in character, and generate long responses.\n```",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "imatrix",
    "pygmalion-2-7b",
    "text-generation",
    "en",
    "license:other",
    "region:us"
  ],
  "likes": 1,
  "downloads": 96,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-13T06:35:46.000Z",
  "created_at": "2024-06-13T04:27:22.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "666a752aa638e57bb782478c",
  "id": "duyntnet/pygmalion-2-7b-imatrix-GGUF",
  "modelId": "duyntnet/pygmalion-2-7b-imatrix-GGUF",
  "sha": "de0b7f02a14f499fc493fa51326282dd954de5b0",
  "createdAt": "2024-06-13T04:27:22.000Z",
  "lastModified": "2024-06-13T06:35:46.000Z",
  "author": "duyntnet",
  "downloads": 96,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 29
}