prithivmlmods/regulus-qwen3-r1-llama-distill-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "datasets": [
      "Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B"
    ],
    "language": [
      "en"
    ],
    "base_model": [
      "prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B"
    ],
    "pipeline_tag": "text-generation",
    "library_name": "transformers",
    "tags": [
      "text-generation-inference",
      "trl",
      "reasoning",
      "code",
      "math"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "datasets": [
        "Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B"
      ],
      "language": [
        "en"
      ],
      "base_model": [
        "prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B"
      ],
      "pipeline_tag": "text-generation",
      "library_name": "transformers",
      "tags": [
        "text-generation-inference",
        "trl",
        "reasoning",
        "code",
        "math"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "> Regulus-Qwen3-R1-Llama-Distill-1.7B is a distilled reasoning model fine-tuned on Qwen/Qwen3-1.7B using Magpie-Align/Magpie-Reasoning-V2-250K-CoT-DeepSeek-R1-Llama-70B. The training leverages distilled traces from DeepSeek-R1-Llama-70B, transferring advanced reasoning patterns into a lightweight 1.7B parameter model. It is specialized for chain-of-thought reasoning across code, math, and science, optimized for efficiency and mid-resource deployment.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\ndatasets:\n- Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B\nlanguage:\n- en\nbase_model:\n- prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B\npipeline_tag: text-generation\nlibrary_name: transformers\ntags:\n- text-generation-inference\n- trl\n- reasoning\n- code\n- math\n---\n\n# **Regulus-Qwen3-R1-Llama-Distill-GGUF**\n\n> Regulus-Qwen3-R1-Llama-Distill-1.7B is a distilled reasoning model fine-tuned on Qwen/Qwen3-1.7B using Magpie-Align/Magpie-Reasoning-V2-250K-CoT-DeepSeek-R1-Llama-70B. The training leverages distilled traces from DeepSeek-R1-Llama-70B, transferring advanced reasoning patterns into a lightweight 1.7B parameter model. It is specialized for chain-of-thought reasoning across code, math, and science, optimized for efficiency and mid-resource deployment.\n\n## Model Files\n\n\n| File Name | Quant Type | File Size |\n| - | - | - |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.BF16.gguf | BF16 | 3.45 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.F16.gguf | F16 | 3.45 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.F32.gguf | F32 | 6.89 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q2_K.gguf | Q2_K | 778 MB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q3_K_L.gguf | Q3_K_L | 1 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q3_K_M.gguf | Q3_K_M | 940 MB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q3_K_S.gguf | Q3_K_S | 867 MB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q4_0.gguf | Q4_0 | 1.05 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q4_1.gguf | Q4_1 | 1.14 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q4_K.gguf | Q4_K | 1.11 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q4_K_M.gguf | Q4_K_M | 1.11 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q4_K_S.gguf | Q4_K_S | 1.06 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q5_0.gguf | Q5_0 | 1.23 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q5_1.gguf | Q5_1 | 1.32 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q5_K.gguf | Q5_K | 1.26 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q5_K_M.gguf | Q5_K_M | 1.26 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q5_K_S.gguf | Q5_K_S | 1.23 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q6_K.gguf | Q6_K | 1.42 GB |\n| Regulus-Qwen3-R1-Llama-Distill-1.7B.Q8_0.gguf | Q8_0 | 1.83 GB |\n\n\n## Quants Usage \n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\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)",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "qwen3",
    "text-generation-inference",
    "trl",
    "reasoning",
    "code",
    "math",
    "text-generation",
    "en",
    "dataset:Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B",
    "base_model:prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B",
    "base_model:quantized:prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-1.7B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 222,
  "gated": false,
  "private": false,
  "last_modified": "2025-08-25T21:12:27.000Z",
  "created_at": "2025-08-25T16:07:54.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "68ac8a5a0280e5390e82187b",
  "id": "prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-GGUF",
  "modelId": "prithivMLmods/Regulus-Qwen3-R1-Llama-Distill-GGUF",
  "sha": "dac72a003ac6d398db6252e2ac3e6642c0694500",
  "createdAt": "2025-08-25T16:07:54.000Z",
  "lastModified": "2025-08-25T21:12:27.000Z",
  "author": "prithivMLmods",
  "downloads": 222,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 22
}