GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

mradermacher/nusantara-2.7b-indo-chat-v0.2-i1-gguf overview

About weighted/imatrix quants of https://huggingface.co/kalisai/Nusantara-2.7b-Indo-Chat-v0.2 static quants are available at https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-GGUF

transformersggufconversationalconvAIidendataset:argilla/OpenHermes2.5-dpo-binarized-alphadataset:wikimedia/wikipediadataset:FreedomIntelligence/evol-instruct-indonesiandataset:Locutusque/hyperion-v2.0base_model:kalisai/Nusantara-2.7b-Indo-Chat-v0.2base_model:quantized:kalisai/Nusantara-2.7b-Indo-Chat-v0.2license:apache-2.0endpoints_compatibleregion:usimatrix
mradermacher/nusantara-2.7b-indo-chat-v0.2-i1-gguf visual
Downloads
89
Likes
0
Pipeline
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

22 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ1_M.gguf GGUF IQ1_M 902.39 MB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ1_S.gguf GGUF IQ1_S 874.73 MB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_M.gguf GGUF IQ2_M 1.07 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_S.gguf GGUF IQ2_S 1.03 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_XS.gguf GGUF IQ2_XS 990.36 MB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_XXS.gguf GGUF IQ2_XXS 948.48 MB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_M.gguf GGUF IQ3_M 1.28 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_S.gguf GGUF IQ3_S 1.23 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_XS.gguf GGUF IQ3_XS 1.19 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_XXS.gguf GGUF IQ3_XXS 1.12 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ4_XS.gguf GGUF IQ4_XS 1.41 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q2_K.gguf GGUF Q2_K 1.09 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q2_K_S.gguf GGUF Q2_K_S 1.06 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q3_K_L.gguf GGUF Q3_K_L 1.39 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q3_K_M.gguf GGUF Q3_K_M 1.33 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q3_K_S.gguf GGUF Q3_K_S 1.23 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q4_0.gguf GGUF 1.47 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q4_K_M.gguf GGUF Q4_K_M 1.62 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q4_K_S.gguf GGUF Q4_K_S 1.53 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q5_K_M.gguf GGUF Q5_K_M 1.84 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q5_K_S.gguf GGUF Q5_K_S 1.77 GB Download
Nusantara-2.7b-Indo-Chat-v0.2.i1-Q6_K.gguf GGUF Q6_K 2.13 GB Download

Model Details Live

Model Slug
mradermacher/nusantara-2.7b-indo-chat-v0.2-i1-gguf
Author
mradermacher
Pipeline Task
Library
transformers
Created
2024-12-22
Last Modified
2024-12-22
Gated
No
Private
No
HF SHA
17b23050b5176ee8461e01ff847142cd2771866f
License
apache-2.0
Language
id, en
Base Model
kalisai/Nusantara-2.7b-Indo-Chat-v0.2

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "kalisai/Nusantara-2.7b-Indo-Chat-v0.2",
    "datasets": [
      "argilla/OpenHermes2.5-dpo-binarized-alpha",
      "wikimedia/wikipedia",
      "FreedomIntelligence/evol-instruct-indonesian",
      "Locutusque/hyperion-v2.0"
    ],
    "language": [
      "id",
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "quantized_by": "mradermacher",
    "tags": [
      "conversational",
      "convAI"
    ],
    "frontmatter": {
      "base_model": "kalisai/Nusantara-2.7b-Indo-Chat-v0.2",
      "datasets": [
        "argilla/OpenHermes2.5-dpo-binarized-alpha",
        "wikimedia/wikipedia",
        "FreedomIntelligence/evol-instruct-indonesian",
        "Locutusque/hyperion-v2.0"
      ],
      "language": [
        "id",
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "quantized_by": "mradermacher",
      "tags": [
        "conversational",
        "convAI"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/kalisai/Nusantara-2.7b-Indo-Chat-v0.2  static quants are available at https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: kalisai/Nusantara-2.7b-Indo-Chat-v0.2\ndatasets:\n- argilla/OpenHermes2.5-dpo-binarized-alpha\n- wikimedia/wikipedia\n- FreedomIntelligence/evol-instruct-indonesian\n- Locutusque/hyperion-v2.0\nlanguage:\n- id\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nquantized_by: mradermacher\ntags:\n- conversational\n- convAI\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/kalisai/Nusantara-2.7b-Indo-Chat-v0.2\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-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/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.2 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.3 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_S.gguf) | i1-IQ3_S | 1.4 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.4 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ3_M.gguf) | i1-IQ3_M | 1.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.5 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.6 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q4_0.gguf) | i1-Q4_0 | 1.7 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.7 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.8 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF/resolve/main/Nusantara-2.7b-Indo-Chat-v0.2.i1-Q6_K.gguf) | i1-Q6_K | 2.4 | 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",
    "conversational",
    "convAI",
    "id",
    "en",
    "dataset:argilla/OpenHermes2.5-dpo-binarized-alpha",
    "dataset:wikimedia/wikipedia",
    "dataset:FreedomIntelligence/evol-instruct-indonesian",
    "dataset:Locutusque/hyperion-v2.0",
    "base_model:kalisai/Nusantara-2.7b-Indo-Chat-v0.2",
    "base_model:quantized:kalisai/Nusantara-2.7b-Indo-Chat-v0.2",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix"
  ],
  "likes": 0,
  "downloads": 89,
  "gated": false,
  "private": false,
  "last_modified": "2024-12-22T15:02:49.000Z",
  "created_at": "2024-12-22T14:13:51.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "67681e9f26eb881162ccbd0e",
  "id": "mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF",
  "modelId": "mradermacher/Nusantara-2.7b-Indo-Chat-v0.2-i1-GGUF",
  "sha": "17b23050b5176ee8461e01ff847142cd2771866f",
  "createdAt": "2024-12-22T14:13:51.000Z",
  "lastModified": "2024-12-22T15:02:49.000Z",
  "author": "mradermacher",
  "downloads": 89,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 25
}