Finetunes
Collection
All finetune models.
•
6 items
•
Updated
This is the 4K version of https://huggingface.co/Walmart-the-bag/zephyr-quiklang-3b with 1000 more samples of openhermes.
This is a finetune of StableLM-Zephyr-3B with 2 datasets, toxic-dpo and openhermes with 10000 samples.
"predict_bleu-4": 31.594154999999997,
"predict_rouge-1": 44.092935,
"predict_rouge-2": 22.276081000000005,
"predict_rouge-l": 34.506909,
"predict_runtime": 121.7549,
"predict_samples_per_second": 0.821,
"predict_steps_per_second": 0.107
Base model
stabilityai/stablelm-zephyr-3b