samuelstolicny/claudie-expert-gemma4-26b-a4b-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en"
    ],
    "base_model": "unsloth/gemma-4-31B-it",
    "tags": [
      "claudie",
      "kubernetes",
      "multi-cloud",
      "infrastructure",
      "text-generation",
      "unsloth"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en"
      ],
      "base_model": "unsloth/gemma-4-31B-it",
      "tags": [
        "claudie",
        "kubernetes",
        "multi-cloud",
        "infrastructure",
        "text-generation",
        "unsloth"
      ]
    },
    "hero_image_url": "",
    "summary": "Fine-tuned Gemma 4 31B-IT specialized on **Claudie** — an open-source platform for managing multi-cloud and hybrid-cloud Kubernetes infrastructure.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\nbase_model: unsloth/gemma-4-31B-it\ntags:\n- claudie\n- kubernetes\n- multi-cloud\n- infrastructure\n- text-generation\n- unsloth\n---\n\n# Claudie Expert — Gemma 4 31B\n\nFine-tuned [Gemma 4 31B-IT](https://huggingface.co/unsloth/gemma-4-31B-it) specialized on **[Claudie](https://claudie.io/)** — an open-source platform for managing multi-cloud and hybrid-cloud Kubernetes infrastructure.\n\n## About Claudie\n\n[Claudie](https://claudie.io/) provisions and manages Kubernetes clusters declaratively across AWS, Azure, GCP, OCI, Hetzner, Exoscale, CloudRift, and OpenStack via the `InputManifest` CRD. Built by [Berops](https://berops.com/).\n\n- **Project:** [github.com/berops/claudie](https://github.com/berops/claudie)\n- **Documentation:** [docs.claudie.io/latest](https://docs.claudie.io/latest/)\n\n## What this model knows\n\nThis model was fine-tuned on ~8,000 Claudie-specific Q&A conversations covering:\n\n- Claudie's 8 microservices (Manager, Terraformer, Ansibler, Kube-Eleven, Kuber, Claudie-Operator, Autoscaler-Adapter)\n- InputManifest CRD authoring for multi-cloud / GPU / autoscaling clusters\n- Debugging stuck states, NATS consumer lag, Terraform state locks, WireGuard issues\n- gRPC service communication, state machine, reconciliation loops\n- Claudie architecture, data flow between services\n- Kubernetes integration patterns\n\n## Files in this repo\n\n| File | Purpose |\n|------|---------|\n| `model-*.safetensors` | Merged bf16 weights (for vLLM, Transformers) |\n| `*.Q4_K_M.gguf` | 4-bit GGUF (for Ollama, llama.cpp) |\n| `chat_template.jinja` | Gemma 4 chat template |\n\n## Usage\n\n### vLLM\n```bash\nvllm serve samuelstolicny/claudie-expert-gemma4-31b --max-model-len 8192\n```\n\n### Ollama\n```bash\nollama run hf.co/samuelstolicny/claudie-expert-gemma4-31b:Q4_K_M\n```\n\n### Transformers\n```python\nfrom transformers import pipeline\npipe = pipeline(\"text-generation\", model=\"samuelstolicny/claudie-expert-gemma4-31b\")\nprint(pipe([{\"role\": \"user\", \"content\": \"How do I add a GPU node pool in Hetzner?\"}]))\n```\n\n## Training\n\n- **Base model:** `unsloth/gemma-4-31B-it`\n- **Method:** LoRA bf16 (rank 64, alpha 128, all-linear)\n- **Framework:** [Unsloth](https://unsloth.ai/)\n- **Dataset:** 8,012 synthetic Q&A conversations generated from the Claudie codebase + docs\n- **Hardware:** 1x RTX PRO 6000 96GB\n\n## License\n\nApache 2.0 — same as the base model and Claudie.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "claudie",
    "kubernetes",
    "multi-cloud",
    "infrastructure",
    "text-generation",
    "unsloth",
    "en",
    "base_model:unsloth/gemma-4-31B-it",
    "base_model:quantized:unsloth/gemma-4-31B-it",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 283,
  "gated": false,
  "private": false,
  "last_modified": "2026-04-13T09:16:11.000Z",
  "created_at": "2026-04-07T15:07:21.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "69d51da96e6723fc596dddab",
  "id": "samuelstolicny/claudie-expert-gemma4-26b-a4b-gguf",
  "modelId": "samuelstolicny/claudie-expert-gemma4-26b-a4b-gguf",
  "sha": "ffd9ea4b6dd5f968e4588311dc3426870aabe168",
  "createdAt": "2026-04-07T15:07:21.000Z",
  "lastModified": "2026-04-13T09:16:11.000Z",
  "author": "samuelstolicny",
  "downloads": 283,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 4
}