Phi-1.5 TOFU full: independently trained checkpoint

Trained from microsoft/phi-1_5 (77aa61eeac94fbf33d492b9f2744c98b42d5b5eb) on locuslab/TOFU full (324592d84ae4f482ac7249b9285c2ecdb53e3a68).

Full-parameter supervised fine-tuning; not a LoRA adapter. This is an independently trained approximation to the original TOFU recipe, not the original locuslab checkpoint. See training_manifest.json for hyperparameters.

Downloads last month
47
Safetensors
Model size
1B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for unl-reset/tofu-phi-1_5-full

Finetuned
(240)
this model

Dataset used to train unl-reset/tofu-phi-1_5-full