RichardErkhov/chargoddard_-_loyal-piano-m7-cdpo-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

loyal-piano-m7-cdpo - GGUF

• —Model creator: https://huggingface.co/chargoddard/
• —Original model: https://huggingface.co/chargoddard/loyal-piano-m7-cdpo/

Original model description: --- license: cc-by-nc-4.0 datasets:

• —HuggingFaceH4/ultrafeedback_binarized language:
• —en ---

Trained for one epoch on ultrafeedback_binarized using cDPO. Evaluation pending.

Some initial benchmark results: | Task |Version| Metric |Value | |Stderr| |---------|------:|--------|-----:|---|-----:| |hellaswag| 0|acc |0.6621|± |0.0047| | | |accnorm|0.8525|± |0.0035| |arcchallenge| 0|acc |0.6348|± |0.0141| | | |acc_norm|0.6698|± |0.0137| |winogrande| 0|acc |0.7861|± |0.0115| |gsm8k| 0|acc |0.5694|± |0.0136|