mradermacher/1.5-pints-16k-v0.1-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "pints-ai/1.5-Pints-16K-v0.1",
    "datasets": [
      "pints-ai/Expository-Prose-V1",
      "HuggingFaceH4/ultrachat_200k",
      "Open-Orca/SlimOrca-Dedup",
      "meta-math/MetaMathQA",
      "HuggingFaceH4/deita-10k-v0-sft",
      "WizardLM/WizardLM_evol_instruct_V2_196k",
      "togethercomputer/llama-instruct",
      "LDJnr/Capybara",
      "HuggingFaceH4/ultrafeedback_binarized"
    ],
    "extra_gated_fields": {
      "Company": "text",
      "Country": "country",
      "I agree to use this model for in accordance to the afore-mentioned Terms of Use": "checkbox",
      "I want to use this model for": {
        "options": [
          "Research",
          "Education",
          {
            "label": "Other",
            "value": "other"
          }
        ],
        "type": "select"
      },
      "Specific date": "date_picker"
    },
    "extra_gated_prompt": "Though best efforts has been made to ensure, as much as possible, that all texts in the training corpora are royalty free, this does not constitute a legal guarantee that such is the case. **By using any of the models, corpora or part thereof, the user agrees to bear full responsibility to do the necessary due diligence to ensure that he / she is in compliance with their local copyright laws. Additionally, the user agrees to bear any damages arising as a direct cause (or otherwise) of using any artifacts released by the pints research team, as well as full responsibility for the consequences of his / her usage (or implementation) of any such released artifacts. The user also indemnifies Pints Research Team (and any of its members or agents) of any damage, related or unrelated, to the release or subsequent usage of any findings, artifacts or code by the team. For the avoidance of doubt, any artifacts released by the Pints Research team are done so in accordance with the 'fair use' clause of Copyright Law, in hopes that this will aid the research community in bringing LLMs to the next frontier.",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "mit",
    "quantized_by": "mradermacher",
    "frontmatter": {
      "base_model": "pints-ai/1.5-Pints-16K-v0.1",
      "datasets": [
        "pints-ai/Expository-Prose-V1",
        "HuggingFaceH4/ultrachat_200k",
        "Open-Orca/SlimOrca-Dedup",
        "meta-math/MetaMathQA",
        "HuggingFaceH4/deita-10k-v0-sft",
        "WizardLM/WizardLM_evol_instruct_V2_196k",
        "togethercomputer/llama-instruct",
        "LDJnr/Capybara",
        "HuggingFaceH4/ultrafeedback_binarized"
      ],
      "extra_gated_fields": [
        "Research",
        "Education",
        "label: Other"
      ],
      "extra_gated_prompt": "Though best efforts has been made to ensure, as much as possible,",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "mit",
      "quantized_by": "mradermacher"
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/pints-ai/1.5-Pints-16K-v0.1  static quants are available at https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: pints-ai/1.5-Pints-16K-v0.1\ndatasets:\n- pints-ai/Expository-Prose-V1\n- HuggingFaceH4/ultrachat_200k\n- Open-Orca/SlimOrca-Dedup\n- meta-math/MetaMathQA\n- HuggingFaceH4/deita-10k-v0-sft\n- WizardLM/WizardLM_evol_instruct_V2_196k\n- togethercomputer/llama-instruct\n- LDJnr/Capybara\n- HuggingFaceH4/ultrafeedback_binarized\nextra_gated_fields:\n  Company: text\n  Country: country\n  I agree to use this model for in accordance to the afore-mentioned Terms of Use: checkbox\n  I want to use this model for:\n    options:\n    - Research\n    - Education\n    - label: Other\n      value: other\n    type: select\n  Specific date: date_picker\nextra_gated_prompt: Though best efforts has been made to ensure, as much as possible,\n  that all texts in the training corpora are royalty free, this does not constitute\n  a legal guarantee that such is the case. **By using any of the models, corpora or\n  part thereof, the user agrees to bear full responsibility to do the necessary due\n  diligence to ensure that he / she is in compliance with their local copyright laws.\n  Additionally, the user agrees to bear any damages arising as a direct cause (or\n  otherwise) of using any artifacts released by the pints research team, as well as\n  full responsibility for the consequences of his / her usage (or implementation)\n  of any such released artifacts. The user also indemnifies Pints Research Team (and\n  any of its members or agents) of any damage, related or unrelated, to the release\n  or subsequent usage of any findings, artifacts or code by the team. For the avoidance\n  of doubt, any artifacts released by the Pints Research team are done so in accordance\n  with the 'fair use' clause of Copyright Law, in hopes that this will aid the research\n  community in bringing LLMs to the next frontier.\nlanguage:\n- en\nlibrary_name: transformers\nlicense: mit\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/pints-ai/1.5-Pints-16K-v0.1\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-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/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.8 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 0.8 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.9 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 |  |\n| [GGUF](https://huggingface.co/mradermacher/1.5-Pints-16K-v0.1-i1-GGUF/resolve/main/1.5-Pints-16K-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | 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",
    "en",
    "dataset:pints-ai/Expository-Prose-V1",
    "dataset:HuggingFaceH4/ultrachat_200k",
    "dataset:Open-Orca/SlimOrca-Dedup",
    "dataset:meta-math/MetaMathQA",
    "dataset:HuggingFaceH4/deita-10k-v0-sft",
    "dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
    "dataset:togethercomputer/llama-instruct",
    "dataset:LDJnr/Capybara",
    "dataset:HuggingFaceH4/ultrafeedback_binarized",
    "base_model:pints-ai/1.5-Pints-16K-v0.1",
    "base_model:quantized:pints-ai/1.5-Pints-16K-v0.1",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 102,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-09T04:02:38.000Z",
  "created_at": "2025-03-08T13:34:15.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "67cc4757af0a3f01c6d6896f",
  "id": "mradermacher/1.5-Pints-16K-v0.1-i1-GGUF",
  "modelId": "mradermacher/1.5-Pints-16K-v0.1-i1-GGUF",
  "sha": "2ceea1ba1f5df9d636a8a6e15d8c4bcd9f506178",
  "createdAt": "2025-03-08T13:34:15.000Z",
  "lastModified": "2025-03-09T04:02:38.000Z",
  "author": "mradermacher",
  "downloads": 102,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}