YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

nexus-tools_sft17-kto2

Training Run: 20251127_164556 HuggingFace: https://huggingface.co/professorsynapse/nexus-tools_sft17-kto2

Available Formats

Merged 16-bit (merged-16bit/) - Full quality merged model (~14GB)
GGUF Quantizations (gguf/) - For llama.cpp/Ollama

Directory Structure

nexus-tools_sft17-kto2/
├── merged-16bit/
├── gguf/
│   ├── nexus-tools_sft17-kto2.gguf (f16)
│   ├── nexus-tools_sft17-kto2-Q4_K_M.gguf
│   ├── nexus-tools_sft17-kto2-Q5_K_M.gguf
│   └── nexus-tools_sft17-kto2-Q8_0.gguf
├── upload_manifest.json
└── README.md

Usage

See the HuggingFace model card for detailed usage instructions.

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support