Instructions to use Wayfinder6/bones-sage-freshdata with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Wayfinder6/bones-sage-freshdata with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir bones-sage-freshdata Wayfinder6/bones-sage-freshdata
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Bones / Sage / Nova LoRA โ freshdata lineage, adapters_freshdata_v7
Automated push, real numbers, no cherry-picking. This is whichever checkpoint is newest at push time, good or bad, per Heuremen's own standing policy: consistent visible history over curated-looking results.
- Final val loss this run: 1.679
- Real curated corpus size at push time: 2268 rows
- Pushed: 2026-08-23 15:39 UTC
Part of the bones-sage-nova-lora family โ this is the actively-iterating line, not the flagship release.
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for Wayfinder6/bones-sage-freshdata
Base model
Qwen/Qwen2.5-14B Finetuned
mlx-community/Qwen2.5-14B-Instruct-4bit