AI & Machine Learning
Omh Model Compression
[omh] Making a model smaller or cheaper by changing its weights: quantization (GPTQ, AWQ, GGUF, bitsandbytes, FP8, quantization-aware training), pruning, or distillation into a smaller student, sized to the target hardware, calibrated on the task's own data, and kept only when it holds quality on the person's own eval. Use when the user says: model-compression, model compression, compress this model, compress the model, compress a model, compress our model, compress my model, quantize this model.
- Publisher / source
- rlaope/oh-my-hermes (found on GitHub top repositories)
- Upstream record
- rlaope/oh-my-hermes
- Version
- Version 1
- Published
- Publication review
- Approved for publication
- Content fingerprint
0be6895dba704545c566c5b9b5ed0a2e90764e317228985442708138f2e7735e