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

qwp4w3hyb/nous-hermes-2-mistral-7b-dpo-imat-gguf overview

Source Model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO Quantized with llama.cpp commit 46acb3676718b983157058aecf729a2064fc7d34 Imatrix was generated from the f16 gguf via this command: ./imatrix -c 512 -m $outpath/$basequantname -f $llamacpppath/groupsmerged.txt -o $out_path/imat-f16-gmerged.dat Using the dataset from here

ggufmistralinstructfinetunechatmlgpt4synthetic datadistillationendataset:teknium/OpenHermes-2.5base_model:NousResearch/Nous-Hermes-2-Mistral-7B-DPObase_model:quantized:NousResearch/Nous-Hermes-2-Mistral-7B-DPOlicense:apache-2.0endpoints_compatibleregion:usconversational
qwp4w3hyb/nous-hermes-2-mistral-7b-dpo-imat-gguf visual
Downloads
155
Likes
0
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

14 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
nous-hermes-2-mistral-7b-dpo-imat-IQ1_S.gguf GGUF IQ1_S 1.50 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ2_M.gguf GGUF IQ2_M 2.33 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ2_S.gguf GGUF IQ2_S 2.15 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ2_XS.gguf GGUF IQ2_XS 2.05 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ3_M.gguf GGUF IQ3_M 3.06 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ3_S.gguf GGUF IQ3_S 2.96 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ3_XS.gguf GGUF IQ3_XS 2.79 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ4_NL.gguf GGUF IQ4_NL 3.84 GB Download
nous-hermes-2-mistral-7b-dpo-imat-IQ4_XS.gguf GGUF IQ4_XS 3.64 GB Download
nous-hermes-2-mistral-7b-dpo-imat-Q4_K_M.gguf GGUF Q4_K_M 4.07 GB Download
nous-hermes-2-mistral-7b-dpo-imat-Q4_K_S.gguf GGUF Q4_K_S 3.86 GB Download
nous-hermes-2-mistral-7b-dpo-imat-Q5_K_M.gguf GGUF Q5_K_M 4.78 GB Download
nous-hermes-2-mistral-7b-dpo-imat-Q5_K_S.gguf GGUF Q5_K_S 4.65 GB Download
nous-hermes-2-mistral-7b-dpo-imat-Q6_K.gguf GGUF Q6_K 5.53 GB Download

Model Details Live

Model Slug
qwp4w3hyb/nous-hermes-2-mistral-7b-dpo-imat-gguf
Author
qwp4w3hyb
Pipeline Task
Library
Created
2024-03-24
Last Modified
2024-03-24
Gated
No
Private
No
HF SHA
168c351db41e460852a4f819d030ddf29e4e5fe4
License
apache-2.0
Language
en
Base Model
NousResearch/Nous-Hermes-2-Mistral-7B-DPO

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
    "tags": [
      "mistral",
      "instruct",
      "finetune",
      "chatml",
      "gpt4",
      "synthetic data",
      "distillation"
    ],
    "model-index": [
      {
        "name": "Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF",
        "results": []
      }
    ],
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "datasets": [
      "teknium/OpenHermes-2.5"
    ],
    "frontmatter": {
      "base_model": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
      "tags": [
        "mistral",
        "instruct",
        "finetune",
        "chatml",
        "gpt4",
        "synthetic data",
        "distillation",
        "name: Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF"
      ],
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "datasets": [
        "teknium/OpenHermes-2.5"
      ]
    },
    "hero_image_url": "",
    "summary": "Source Model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO Quantized with llama.cpp commit 46acb3676718b983157058aecf729a2064fc7d34 Imatrix was generated from the f16 gguf via this command: ./imatrix -c 512 -m $out_path/$base_quant_name -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat Using the dataset from here",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO\ntags:\n- mistral\n- instruct\n- finetune\n- chatml\n- gpt4\n- synthetic data\n- distillation\nmodel-index:\n- name: Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF\n  results: []\nlicense: apache-2.0\nlanguage:\n- en\ndatasets:\n- teknium/OpenHermes-2.5\n---\n\n# Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF\n\nSource Model: [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)\n\nQuantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [46acb3676718b983157058aecf729a2064fc7d34](https://github.com/ggerganov/llama.cpp/commit/46acb3676718b983157058aecf729a2064fc7d34)\n\nImatrix was generated from the f16 gguf via this command:\n\n./imatrix -c 512 -m $out_path/$base_quant_name -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat\n\nUsing the dataset from [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "mistral",
    "instruct",
    "finetune",
    "chatml",
    "gpt4",
    "synthetic data",
    "distillation",
    "en",
    "dataset:teknium/OpenHermes-2.5",
    "base_model:NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
    "base_model:quantized:NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 155,
  "gated": false,
  "private": false,
  "last_modified": "2024-03-24T04:56:36.000Z",
  "created_at": "2024-03-24T03:42:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "65ffa13f6aa2a661ddd0f800",
  "id": "qwp4w3hyb/Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF",
  "modelId": "qwp4w3hyb/Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF",
  "sha": "168c351db41e460852a4f819d030ddf29e4e5fe4",
  "createdAt": "2024-03-24T03:42:55.000Z",
  "lastModified": "2024-03-24T04:56:36.000Z",
  "author": "qwp4w3hyb",
  "downloads": 155,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 17
}