diff --git a/docs/attacks/quantile.html b/docs/attacks/quantile.html
index 6e42fbd..c03cb29 100644
--- a/docs/attacks/quantile.html
+++ b/docs/attacks/quantile.html
@@ -180,7 +180,7 @@ Args
The function to use to form a batch from a list of elements of train_dataset or eval_dataset. Will
default to [default_data_collator] if no tokenizer is provided, an instance of
[DataCollatorWithPadding] otherwise.
-train_dataset (torch.utils.data.Dataset or torch.utils.data.IterableDataset, optional):
+train_dataset (Union[torch.utils.data.Dataset, torch.utils.data.IterableDataset, datasets.Dataset], optional):
The dataset to use for training. If it is a [~datasets.Dataset], columns not accepted by the
model.forward() method are automatically removed.
Note that if it's a <code>torch.utils.data.IterableDataset</code> with some randomization and you are training in a
@@ -189,7 +189,7 @@ Args
manually set the seed of this <code>generator</code> at each epoch) or have a <code>set\_epoch()</code> method that internally
sets the seed of the RNGs used.
-eval_dataset (Union[torch.utils.data.Dataset, Dict[str, torch.utils.data.Dataset]), optional):
+
eval_dataset (Union[torch.utils.data.Dataset, Dict[str, torch.utils.data.Dataset, datasets.Dataset]), optional):
The dataset to use for evaluation. If it is a [~datasets.Dataset], columns not accepted by the
model.forward() method are automatically removed. If it is a dictionary, it will evaluate on each
dataset prepending the dictionary key to the metric name.
diff --git a/docs/config.html b/docs/config.html
index fa45df3..9c1fb4f 100644
--- a/docs/config.html
+++ b/docs/config.html
@@ -172,7 +172,7 @@
Module mimir.config
max_substrs: Optional[int] = 20
"""If full_doc, determines the maximum number of sample substrs to evaluate on"""
dump_cache: Optional[bool] = False
- "Dump data to cache? Exits program after dumping"
+ """Dump data to cache? Exits program after dumping"""
load_from_cache: Optional[bool] = False
"""Load data from cache?"""
load_from_hf: Optional[bool] = True
@@ -216,9 +216,9 @@ Module mimir.config
pre_perturb_span_length: Optional[int] = 5
"""Span length for pre-perturbation"""
tok_by_tok: Optional[bool] = False
- """FPRs at which to compute TPR"""
- fpr_list: Optional[List[float]] = field(default_factory=lambda: [0.001, 0.01])
"""Process data token-wise?"""
+ fpr_list: Optional[List[float]] = field(default_factory=lambda: [0.001, 0.01])
+ """FPRs at which to compute TPR"""
random_seed: Optional[int] = 0
"""Random seed"""
ref_config: Optional[ReferenceConfig] = None
@@ -400,7 +400,7 @@ Class variables
max_substrs: Optional[int] = 20
"""If full_doc, determines the maximum number of sample substrs to evaluate on"""
dump_cache: Optional[bool] = False
- "Dump data to cache? Exits program after dumping"
+ """Dump data to cache? Exits program after dumping"""
load_from_cache: Optional[bool] = False
"""Load data from cache?"""
load_from_hf: Optional[bool] = True
@@ -444,9 +444,9 @@ Class variables
pre_perturb_span_length: Optional[int] = 5
"""Span length for pre-perturbation"""
tok_by_tok: Optional[bool] = False
- """FPRs at which to compute TPR"""
- fpr_list: Optional[List[float]] = field(default_factory=lambda: [0.001, 0.01])
"""Process data token-wise?"""
+ fpr_list: Optional[List[float]] = field(default_factory=lambda: [0.001, 0.01])
+ """FPRs at which to compute TPR"""
random_seed: Optional[int] = 0
"""Random seed"""
ref_config: Optional[ReferenceConfig] = None
@@ -539,7 +539,7 @@ Class variables
var fpr_list : Optional[List[float]]
-
+FPRs at which to compute TPR
var full_doc : Optional[bool]
@@ -639,7 +639,7 @@ Class variables
var tok_by_tok : Optional[bool]
-FPRs at which to compute TPR
var token_frequency_map : Optional[str]