GraySoft
Projects Models About FAQ Contact Download guIDE →

mradermacher/gemma-orchid-7b-dpo-i1-gguf IQ3_XXS 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

mradermacher/gemma-orchid-7b-dpo-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/macadeliccc/gemma-orchid-7b-dpo static quants are available at https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-GGUF

transformersggufendataset:Thermostatic/flowersdataset:jondurbin/truthy-dpo-v0.1dataset:Intel/orca_dpo_pairsdataset:glaiveai/glaive-function-calling-v2base_model:macadeliccc/gemma-orchid-7b-dpobase_model:quantized:macadeliccc/gemma-orchid-7b-dpolicense:otherendpoints_compatibleregion:usimatrix
mradermacher/gemma-orchid-7b-dpo-i1-gguf visual
Downloads
85
Likes
0
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

24 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
gemma-orchid-7b-dpo.i1-IQ1_M.gguf GGUF IQ1_M 2.16 GB Download
gemma-orchid-7b-dpo.i1-IQ1_S.gguf GGUF IQ1_S 2.01 GB Download
gemma-orchid-7b-dpo.i1-IQ2_M.gguf GGUF IQ2_M 2.92 GB Download
gemma-orchid-7b-dpo.i1-IQ2_S.gguf GGUF IQ2_S 2.72 GB Download
gemma-orchid-7b-dpo.i1-IQ2_XS.gguf GGUF IQ2_XS 2.62 GB Download
gemma-orchid-7b-dpo.i1-IQ2_XXS.gguf GGUF IQ2_XXS 2.41 GB Download
gemma-orchid-7b-dpo.i1-IQ3_M.gguf GGUF IQ3_M 3.82 GB Download
gemma-orchid-7b-dpo.i1-IQ3_S.gguf GGUF IQ3_S 3.71 GB Download
gemma-orchid-7b-dpo.i1-IQ3_XS.gguf GGUF IQ3_XS 3.54 GB Download
gemma-orchid-7b-dpo.i1-IQ3_XXS.gguf GGUF IQ3_XXS 3.25 GB Download
gemma-orchid-7b-dpo.i1-IQ4_XS.gguf GGUF IQ4_XS 4.44 GB Download
gemma-orchid-7b-dpo.i1-Q2_K.gguf GGUF Q2_K 3.24 GB Download
gemma-orchid-7b-dpo.i1-Q3_K_L.gguf GGUF Q3_K_L 4.39 GB Download
gemma-orchid-7b-dpo.i1-Q3_K_M.gguf GGUF Q3_K_M 4.07 GB Download
gemma-orchid-7b-dpo.i1-Q3_K_S.gguf GGUF Q3_K_S 3.71 GB Download
gemma-orchid-7b-dpo.i1-Q4_0.gguf GGUF 4.68 GB Download
gemma-orchid-7b-dpo.i1-Q4_0_4_4.gguf GGUF 4.67 GB Download
gemma-orchid-7b-dpo.i1-Q4_0_4_8.gguf GGUF 4.67 GB Download
gemma-orchid-7b-dpo.i1-Q4_0_8_8.gguf GGUF 4.67 GB Download
gemma-orchid-7b-dpo.i1-Q4_K_M.gguf GGUF Q4_K_M 4.96 GB Download
gemma-orchid-7b-dpo.i1-Q4_K_S.gguf GGUF Q4_K_S 4.70 GB Download
gemma-orchid-7b-dpo.i1-Q5_K_M.gguf GGUF Q5_K_M 5.72 GB Download
gemma-orchid-7b-dpo.i1-Q5_K_S.gguf GGUF Q5_K_S 5.57 GB Download
gemma-orchid-7b-dpo.i1-Q6_K.gguf GGUF Q6_K 6.53 GB Download

Model Details Live

Model Slug
mradermacher/gemma-orchid-7b-dpo-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2024-11-12
Last Modified
2024-11-12
Gated
No
Private
No
HF SHA
2bcd2b4118d2e352b8322cdc255a72414f6af593
License
other
Language
en
Base Model
macadeliccc/gemma-orchid-7b-dpo

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "macadeliccc/gemma-orchid-7b-dpo",
    "datasets": [
      "Thermostatic/flowers",
      "jondurbin/truthy-dpo-v0.1",
      "Intel/orca_dpo_pairs",
      "glaiveai/glaive-function-calling-v2"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://ai.google.dev/gemma/terms",
    "license_name": "gemma-terms-of-use",
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "macadeliccc/gemma-orchid-7b-dpo",
      "datasets": [
        "Thermostatic/flowers",
        "jondurbin/truthy-dpo-v0.1",
        "Intel/orca_dpo_pairs",
        "glaiveai/glaive-function-calling-v2"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://ai.google.dev/gemma/terms",
      "license_name": "gemma-terms-of-use",
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/macadeliccc/gemma-orchid-7b-dpo  static quants are available at https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: macadeliccc/gemma-orchid-7b-dpo\ndatasets:\n- Thermostatic/flowers\n- jondurbin/truthy-dpo-v0.1\n- Intel/orca_dpo_pairs\n- glaiveai/glaive-function-calling-v2\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://ai.google.dev/gemma/terms\nlicense_name: gemma-terms-of-use\nquantized_by: mradermacher\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\nweighted/imatrix quants of https://huggingface.co/macadeliccc/gemma-orchid-7b-dpo\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ1_S.gguf) | i1-IQ1_S | 2.3 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q2_K.gguf) | i1-Q2_K | 3.6 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.6 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ3_S.gguf) | i1-IQ3_S | 4.1 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.1 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ3_M.gguf) | i1-IQ3_M | 4.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.8 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 5.1 | fast on arm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 5.1 | fast on arm+i8mm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 5.1 | fast on arm+sve, low quality |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q4_0.gguf) | i1-Q4_0 | 5.1 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.1 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.4 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/gemma-orchid-7b-dpo-i1-GGUF/resolve/main/gemma-orchid-7b-dpo.i1-Q6_K.gguf) | i1-Q6_K | 7.1 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "en",
    "dataset:Thermostatic/flowers",
    "dataset:jondurbin/truthy-dpo-v0.1",
    "dataset:Intel/orca_dpo_pairs",
    "dataset:glaiveai/glaive-function-calling-v2",
    "base_model:macadeliccc/gemma-orchid-7b-dpo",
    "base_model:quantized:macadeliccc/gemma-orchid-7b-dpo",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 0,
  "downloads": 85,
  "gated": false,
  "private": false,
  "last_modified": "2024-11-12T23:36:10.000Z",
  "created_at": "2024-11-12T19:50:39.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "6733b18faca50d0de3b4105c",
  "id": "mradermacher/gemma-orchid-7b-dpo-i1-GGUF",
  "modelId": "mradermacher/gemma-orchid-7b-dpo-i1-GGUF",
  "sha": "2bcd2b4118d2e352b8322cdc255a72414f6af593",
  "createdAt": "2024-11-12T19:50:39.000Z",
  "lastModified": "2024-11-12T23:36:10.000Z",
  "author": "mradermacher",
  "downloads": 85,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}