Add TF weights
#4
by
neggles
- opened
Model converted by the transformers' pt_to_tf CLI. All converted model outputs and hidden layers were validated against its PyTorch counterpart.
Maximum crossload output difference=1.383e-05; Maximum crossload hidden layer difference=1.526e-02;
Maximum conversion output difference=1.383e-05; Maximum conversion hidden layer difference=1.526e-02;
CAUTION: The maximum admissible error was manually increased to 0.1!
Note: Actual output differences are:
List of maximum output differences above the threshold (1e-05):
logits: 1.180e-05
List of maximum hidden layer differences above the threshold (1e-05):
hidden_states[1]: 3.755e-05
hidden_states[2]: 2.975e-04
hidden_states[3]: 6.866e-03
hidden_states[4]: 9.727e-05
Minor error in conversion code when I created this. See GH PR for details.
Rocketknight1
changed pull request status to
merged