mradermacher/rombos_replete-coder-llama3-8b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "rombodawg/rombos_Replete-Coder-Llama3-8B",
    "datasets": [
      "Replete-AI/code_bagel_hermes-2.5",
      "Replete-AI/code_bagel",
      "Replete-AI/OpenHermes-2.5-Uncensored",
      "teknium/OpenHermes-2.5",
      "layoric/tiny-codes-alpaca",
      "glaiveai/glaive-code-assistant-v3",
      "ajibawa-2023/Code-290k-ShareGPT",
      "TIGER-Lab/MathInstruct",
      "chargoddard/commitpack-ft-instruct-rated",
      "iamturun/code_instructions_120k_alpaca",
      "ise-uiuc/Magicoder-Evol-Instruct-110K",
      "cognitivecomputations/dolphin-coder",
      "nickrosh/Evol-Instruct-Code-80k-v1",
      "coseal/CodeUltraFeedback_binarized",
      "glaiveai/glaive-function-calling-v2",
      "CyberNative/Code_Vulnerability_Security_DPO",
      "jondurbin/airoboros-2.2",
      "camel-ai",
      "lmsys/lmsys-chat-1m",
      "CollectiveCognition/chats-data-2023-09-22",
      "CoT-Alpaca-GPT4",
      "WizardLM/WizardLM_evol_instruct_70k",
      "WizardLM/WizardLM_evol_instruct_V2_196k",
      "teknium/GPT4-LLM-Cleaned",
      "GPTeacher",
      "OpenGPT",
      "meta-math/MetaMathQA",
      "Open-Orca/SlimOrca",
      "garage-bAInd/Open-Platypus",
      "anon8231489123/ShareGPT_Vicuna_unfiltered",
      "Unnatural-Instructions-GPT4"
    ],
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://llama.meta.com/llama3/license/",
    "license_name": "llama-3",
    "quantized_by": "mradermacher",
    "tags": [
      "text-generation-inference",
      "transformers",
      "unsloth",
      "llama"
    ],
    "frontmatter": {
      "base_model": "rombodawg/rombos_Replete-Coder-Llama3-8B",
      "datasets": [
        "Replete-AI/code_bagel_hermes-2.5",
        "Replete-AI/code_bagel",
        "Replete-AI/OpenHermes-2.5-Uncensored",
        "teknium/OpenHermes-2.5",
        "layoric/tiny-codes-alpaca",
        "glaiveai/glaive-code-assistant-v3",
        "ajibawa-2023/Code-290k-ShareGPT",
        "TIGER-Lab/MathInstruct",
        "chargoddard/commitpack-ft-instruct-rated",
        "iamturun/code_instructions_120k_alpaca",
        "ise-uiuc/Magicoder-Evol-Instruct-110K",
        "cognitivecomputations/dolphin-coder",
        "nickrosh/Evol-Instruct-Code-80k-v1",
        "coseal/CodeUltraFeedback_binarized",
        "glaiveai/glaive-function-calling-v2",
        "CyberNative/Code_Vulnerability_Security_DPO",
        "jondurbin/airoboros-2.2",
        "camel-ai",
        "lmsys/lmsys-chat-1m",
        "CollectiveCognition/chats-data-2023-09-22",
        "CoT-Alpaca-GPT4",
        "WizardLM/WizardLM_evol_instruct_70k",
        "WizardLM/WizardLM_evol_instruct_V2_196k",
        "teknium/GPT4-LLM-Cleaned",
        "GPTeacher",
        "OpenGPT",
        "meta-math/MetaMathQA",
        "Open-Orca/SlimOrca",
        "garage-bAInd/Open-Platypus",
        "anon8231489123/ShareGPT_Vicuna_unfiltered",
        "Unnatural-Instructions-GPT4"
      ],
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "other",
      "license_link": "https://llama.meta.com/llama3/license/",
      "license_name": "llama-3",
      "quantized_by": "mradermacher",
      "tags": [
        "text-generation-inference",
        "transformers",
        "unsloth",
        "llama"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About      weighted/imatrix quants of https://huggingface.co/rombodawg/rombos_Replete-Coder-Llama3-8B  static quants are available at https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: rombodawg/rombos_Replete-Coder-Llama3-8B\ndatasets:\n- Replete-AI/code_bagel_hermes-2.5\n- Replete-AI/code_bagel\n- Replete-AI/OpenHermes-2.5-Uncensored\n- teknium/OpenHermes-2.5\n- layoric/tiny-codes-alpaca\n- glaiveai/glaive-code-assistant-v3\n- ajibawa-2023/Code-290k-ShareGPT\n- TIGER-Lab/MathInstruct\n- chargoddard/commitpack-ft-instruct-rated\n- iamturun/code_instructions_120k_alpaca\n- ise-uiuc/Magicoder-Evol-Instruct-110K\n- cognitivecomputations/dolphin-coder\n- nickrosh/Evol-Instruct-Code-80k-v1\n- coseal/CodeUltraFeedback_binarized\n- glaiveai/glaive-function-calling-v2\n- CyberNative/Code_Vulnerability_Security_DPO\n- jondurbin/airoboros-2.2\n- camel-ai\n- lmsys/lmsys-chat-1m\n- CollectiveCognition/chats-data-2023-09-22\n- CoT-Alpaca-GPT4\n- WizardLM/WizardLM_evol_instruct_70k\n- WizardLM/WizardLM_evol_instruct_V2_196k\n- teknium/GPT4-LLM-Cleaned\n- GPTeacher\n- OpenGPT\n- meta-math/MetaMathQA\n- Open-Orca/SlimOrca\n- garage-bAInd/Open-Platypus\n- anon8231489123/ShareGPT_Vicuna_unfiltered\n- Unnatural-Instructions-GPT4\nlanguage:\n- en\nlibrary_name: transformers\nlicense: other\nlicense_link: https://llama.meta.com/llama3/license/\nlicense_name: llama-3\nquantized_by: mradermacher\ntags:\n- text-generation-inference\n- transformers\n- unsloth\n- llama\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/rombodawg/rombos_Replete-Coder-Llama3-8B\n\n<!-- provided-files -->\nstatic quants are available at https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-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/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF/resolve/main/rombos_Replete-Coder-Llama3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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",
    "text-generation-inference",
    "unsloth",
    "llama",
    "en",
    "dataset:Replete-AI/code_bagel_hermes-2.5",
    "dataset:Replete-AI/code_bagel",
    "dataset:Replete-AI/OpenHermes-2.5-Uncensored",
    "dataset:teknium/OpenHermes-2.5",
    "dataset:layoric/tiny-codes-alpaca",
    "dataset:glaiveai/glaive-code-assistant-v3",
    "dataset:ajibawa-2023/Code-290k-ShareGPT",
    "dataset:TIGER-Lab/MathInstruct",
    "dataset:chargoddard/commitpack-ft-instruct-rated",
    "dataset:iamturun/code_instructions_120k_alpaca",
    "dataset:ise-uiuc/Magicoder-Evol-Instruct-110K",
    "dataset:cognitivecomputations/dolphin-coder",
    "dataset:nickrosh/Evol-Instruct-Code-80k-v1",
    "dataset:coseal/CodeUltraFeedback_binarized",
    "dataset:glaiveai/glaive-function-calling-v2",
    "dataset:CyberNative/Code_Vulnerability_Security_DPO",
    "dataset:jondurbin/airoboros-2.2",
    "dataset:camel-ai",
    "dataset:lmsys/lmsys-chat-1m",
    "dataset:CollectiveCognition/chats-data-2023-09-22",
    "dataset:CoT-Alpaca-GPT4",
    "dataset:WizardLM/WizardLM_evol_instruct_70k",
    "dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
    "dataset:teknium/GPT4-LLM-Cleaned",
    "dataset:GPTeacher",
    "dataset:OpenGPT",
    "dataset:meta-math/MetaMathQA",
    "dataset:Open-Orca/SlimOrca",
    "dataset:garage-bAInd/Open-Platypus",
    "dataset:anon8231489123/ShareGPT_Vicuna_unfiltered",
    "dataset:Unnatural-Instructions-GPT4",
    "base_model:rombodawg/rombos_Replete-Coder-Llama3-8B",
    "base_model:quantized:rombodawg/rombos_Replete-Coder-Llama3-8B",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 1,
  "downloads": 744,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-11T16:40:45.000Z",
  "created_at": "2024-10-07T09:26:17.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "6703a93977f7e874a2be4097",
  "id": "mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF",
  "modelId": "mradermacher/rombos_Replete-Coder-Llama3-8B-i1-GGUF",
  "sha": "b42440fbe87c7154d2f08cc9e08d46a3ada3d823",
  "createdAt": "2024-10-07T09:26:17.000Z",
  "lastModified": "2024-10-11T16:40:45.000Z",
  "author": "mradermacher",
  "downloads": 744,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 27
}