Skip to content

logits

shrinkai.distillation.losses.logits

Logit-based Knowledge Distillation loss functions.

This module provides various loss functions that operate on the final output logits of the student and teacher models. Logit-based distillation (or "response-based" distillation) is the most common form of Knowledge Distillation.

These methods typically apply temperature scaling to the models' logits to soften the probability distributions. This exposes the "dark knowledge" of the teacher (i.e., the relative probabilities assigned to non-target classes), allowing the student to learn the teacher's generalization capabilities.

Available Losses
  • HintonLoss: The standard KD loss (Cross-Entropy + KL Divergence).
  • PureKDLoss: Pure distillation without ground-truth labels (KL Divergence only).
  • ReverseKLLoss: Mode-seeking distillation, highly effective for LLMs.
  • BCEKDLoss: Distillation for multi-label classification tasks (Sigmoid + BCE).
  • JSDLoss: Symmetric distillation using Jensen-Shannon Divergence.

Examples:

>>> from shrinkai.distillation.losses import HintonLoss
>>> criterion = HintonLoss(temperature=4.0, alpha=0.5)
>>> loss = criterion(student_logits, teacher_logits, labels)

Classes:

Name Description
BCEKDLoss

Knowledge Distillation loss for Multi-Label classification tasks.
HintonLoss

Knowledge Distillation loss (Geoffrey Hinton et al. (2015)).
JSDLoss

Jensen-Shannon Divergence (JSD) loss for Knowledge Distillation.
PureKDLoss

Pure Knowledge Distillation loss.
ReverseKLLoss

Reverse Kullback-Leibler divergence for Knowledge Distillation (Gu et al. (2024),

Functions:

Name Description
expects_logits

Decorator to automatically extract logits from FeatureExtractor tuples.

Classes

BCEKDLoss

Bases: BaseDistillationLoss

Knowledge Distillation loss for Multi-Label classification tasks.

Unlike HintonLoss which uses Softmax (classes are mutually exclusive), this loss uses Sigmoid to treat each class independently. It computes the Binary Cross Entropy (BCE) between the student's logits and the teacher's softened targets.

Equation
\[L = (1 - \alpha) \cdot \text{BCE}(z_s, y) + \alpha \cdot T^2 \cdot \text{BCE}\left(\frac{z_s}{T}, \text{sigmoid}\left(\frac{z_t}{T}\right)\right)\]

Attributes:

Name Type Description
temperature float

Softening factor for logits. Must be > 0.
alpha float

Weight balancing factor. Must be in range [0.0, 1.0].

Methods:

Name Description
forward

Computes combined hard BCE and soft BCE losses.
Source code in src/shrinkai/distillation/losses/logits.py 
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
class BCEKDLoss(BaseDistillationLoss):
    r"""Knowledge Distillation loss for Multi-Label classification tasks.

    Unlike HintonLoss which uses Softmax (classes are mutually exclusive),
    this loss uses Sigmoid to treat each class independently. It computes
    the Binary Cross Entropy (BCE) between the student's logits and the
    teacher's softened targets.

    Equation:
        $$L = (1 - \alpha) \cdot \text{BCE}(z_s, y) + \alpha \cdot T^2 \cdot \text{BCE}\left(\frac{z_s}{T}, \text{sigmoid}\left(\frac{z_t}{T}\right)\right)$$

    Attributes:
        temperature (float): Softening factor for logits. Must be > 0.
        alpha (float): Weight balancing factor. Must be in range [0.0, 1.0].
    """  # noqa: E501

    def __init__(self, temperature: float = 2.0, alpha: float = 0.5) -> None:
        super().__init__()
        if temperature <= 0:
            raise ValueError(f"Temperature must be positive, got {temperature}")
        if not (0.0 <= alpha <= 1.0):
            raise ValueError(f"Alpha must be between 0.0 and 1.0, got {alpha}")

        self.temperature = float(temperature)
        self.alpha = float(alpha)
        self.bce_with_logits = nn.BCEWithLogitsLoss()

    @expects_logits
    def forward(
        self,
        student_outputs: torch.Tensor,
        teacher_outputs: torch.Tensor,
        labels: torch.Tensor | None = None,
    ) -> torch.Tensor:
        """Computes combined hard BCE and soft BCE losses.

        Args:
            student_outputs: Raw unnormalized logits from the student model
                (Shape: [B, C] or [B, S, C]).
            teacher_outputs: Raw unnormalized logits from the teacher model
                (Shape: [B, C] or [B, S, C]).
            labels: Ground-truth labels (ignored, kept for API compatibility).

        Returns:
            torch.Tensor: Scalar loss value.

        Raises:
            ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
        """
        if student_outputs.shape != teacher_outputs.shape:
            raise ValueError("Shape mismatch between student and teacher logits.")

        with torch.no_grad():
            soft_targets = torch.sigmoid(teacher_outputs / self.temperature)

        kd_loss = F.binary_cross_entropy_with_logits(
            student_outputs / self.temperature, soft_targets
        )
        kd_loss = kd_loss * (self.temperature**2)

        if self.alpha == 1.0:
            return kd_loss

        if labels is None:
            raise ValueError("Ground-truth `labels` are required when `alpha` < 1.0.")

        hard_loss = self.bce_with_logits(student_outputs, labels.float())
        return (1.0 - self.alpha) * hard_loss + self.alpha * kd_loss
Methods:
forward 
forward(
    student_outputs: Tensor,
    teacher_outputs: Tensor,
    labels: Tensor | None = None,
) -> torch.Tensor

Computes combined hard BCE and soft BCE losses.

Parameters:

Name Type Description Default
student_outputs Tensor

Raw unnormalized logits from the student model (Shape: [B, C] or [B, S, C]).

 required
teacher_outputs Tensor

Raw unnormalized logits from the teacher model (Shape: [B, C] or [B, S, C]).

 required
labels Tensor | None

Ground-truth labels (ignored, kept for API compatibility).

 None

Returns:

Type Description
Tensor

torch.Tensor: Scalar loss value.

Raises:

Type Description
ValueError

If shapes of student_outputs and teacher_outputs mismatch.
Source code in src/shrinkai/distillation/losses/logits.py 
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
@expects_logits
def forward(
    self,
    student_outputs: torch.Tensor,
    teacher_outputs: torch.Tensor,
    labels: torch.Tensor | None = None,
) -> torch.Tensor:
    """Computes combined hard BCE and soft BCE losses.

    Args:
        student_outputs: Raw unnormalized logits from the student model
            (Shape: [B, C] or [B, S, C]).
        teacher_outputs: Raw unnormalized logits from the teacher model
            (Shape: [B, C] or [B, S, C]).
        labels: Ground-truth labels (ignored, kept for API compatibility).

    Returns:
        torch.Tensor: Scalar loss value.

    Raises:
        ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
    """
    if student_outputs.shape != teacher_outputs.shape:
        raise ValueError("Shape mismatch between student and teacher logits.")

    with torch.no_grad():
        soft_targets = torch.sigmoid(teacher_outputs / self.temperature)

    kd_loss = F.binary_cross_entropy_with_logits(
        student_outputs / self.temperature, soft_targets
    )
    kd_loss = kd_loss * (self.temperature**2)

    if self.alpha == 1.0:
        return kd_loss

    if labels is None:
        raise ValueError("Ground-truth `labels` are required when `alpha` < 1.0.")

    hard_loss = self.bce_with_logits(student_outputs, labels.float())
    return (1.0 - self.alpha) * hard_loss + self.alpha * kd_loss

HintonLoss

Bases: BaseDistillationLoss

Knowledge Distillation loss (Geoffrey Hinton et al. (2015)).

Combines standard task loss (Cross-Entropy with hard ground-truth labels) and distillation loss (Kullback-Leibler divergence on softened probabilities produced by a teacher model at a given temperature).

Equation
\[L = (1 - \alpha) \cdot L_{ce}(z_s, y) + \alpha \cdot T^2 \cdot L_{kl}\left(\text{softmax}\left(\frac{z_s}{T}\right), \text{softmax}\left(\frac{z_t}{T}\right)\right)\]

Attributes:

Name Type Description
temperature float

Softening factor for logits. Higher values produce smoother probability distributions over classes. Must be > 0.
alpha float

Weight balancing factor between hard label loss and distillation loss. Must be in range [0.0, 1.0].

Methods:

Name Description
__init__

Initializes the HintonLoss module.
forward

Computes combined Cross-Entropy and KD divergence losses.
Source code in src/shrinkai/distillation/losses/logits.py 
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
class HintonLoss(BaseDistillationLoss):
    r"""Knowledge Distillation loss (Geoffrey Hinton et al. (2015)).

    Combines standard task loss (Cross-Entropy with hard ground-truth labels)
    and distillation loss (Kullback-Leibler divergence on softened probabilities
    produced by a teacher model at a given temperature).

    Equation:
        $$L = (1 - \alpha) \cdot L_{ce}(z_s, y) + \alpha \cdot T^2 \cdot L_{kl}\left(\text{softmax}\left(\frac{z_s}{T}\right), \text{softmax}\left(\frac{z_t}{T}\right)\right)$$

    Attributes:
        temperature (float): Softening factor for logits. Higher values produce
            smoother probability distributions over classes. Must be > 0.
        alpha (float): Weight balancing factor between hard label loss and
            distillation loss. Must be in range [0.0, 1.0].
    """  # noqa: E501

    def __init__(self, temperature: float = 4.0, alpha: float = 0.5) -> None:
        """Initializes the HintonLoss module.

        Args:
            temperature: Temperature scaling factor (T > 0). Defaults to 4.0.
            alpha: Weight for distillation loss (0.0 <= alpha <= 1.0). Defaults to 0.5.

        Raises:
            ValueError: If `temperature` <= 0 or `alpha` is not in [0.0, 1.0].
        """
        super().__init__()

        if temperature <= 0:
            raise ValueError(f"Temperature must be positive, current temperature is {temperature}")
        if not (0.0 <= alpha <= 1.0):
            raise ValueError(f"Alpha must be between 0.0 and 1.0, current alpha is {alpha}")

        self.temperature = float(temperature)
        self.alpha = float(alpha)
        self.kl_div = nn.KLDivLoss(reduction="batchmean")
        self.cross_entropy = nn.CrossEntropyLoss()

    @expects_logits
    def forward(
        self,
        student_outputs: torch.Tensor,
        teacher_outputs: torch.Tensor,
        labels: torch.Tensor | None = None,
    ) -> torch.Tensor:
        """Computes combined Cross-Entropy and KD divergence losses.

        Args:
            student_outputs: Raw unnormalized logits from the student model (Shape: [B, C]).
            teacher_outputs: Raw unnormalized logits from the teacher model (Shape: [B, C]).
            labels: Ground-truth class indices (Shape: [B]). Optional if alpha == 1.0.

        Returns:
            torch.Tensor: Weighted scalar loss value.

        Raises:
            ValueError: If `labels` is None when `alpha` < 1.0.
            ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
        """
        if student_outputs.shape != teacher_outputs.shape:
            raise ValueError(
                f"Shape mismatch: student logits {student_outputs.shape} "
                f"vs teacher logits {teacher_outputs.shape}"
            )

        soft_student = F.log_softmax(student_outputs / self.temperature, dim=-1)
        soft_teacher = F.softmax(teacher_outputs / self.temperature, dim=-1)
        kd_loss = self.kl_div(soft_student, soft_teacher) * (self.temperature**2)

        if self.alpha == 1.0:
            return kd_loss

        if labels is None:
            raise ValueError("Ground-truth `labels` are required when `alpha` < 1.0.")

        ce_loss = self.cross_entropy(student_outputs, labels)
        return (1.0 - self.alpha) * ce_loss + self.alpha * kd_loss
Methods:
__init__ 
__init__(
    temperature: float = 4.0, alpha: float = 0.5
) -> None

Initializes the HintonLoss module.

Parameters:

Name Type Description Default
temperature float

Temperature scaling factor (T > 0). Defaults to 4.0.

 4.0
alpha float

Weight for distillation loss (0.0 <= alpha <= 1.0). Defaults to 0.5.

 0.5

Raises:

Type Description
ValueError

If temperature <= 0 or alpha is not in [0.0, 1.0].
Source code in src/shrinkai/distillation/losses/logits.py 
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
def __init__(self, temperature: float = 4.0, alpha: float = 0.5) -> None:
    """Initializes the HintonLoss module.

    Args:
        temperature: Temperature scaling factor (T > 0). Defaults to 4.0.
        alpha: Weight for distillation loss (0.0 <= alpha <= 1.0). Defaults to 0.5.

    Raises:
        ValueError: If `temperature` <= 0 or `alpha` is not in [0.0, 1.0].
    """
    super().__init__()

    if temperature <= 0:
        raise ValueError(f"Temperature must be positive, current temperature is {temperature}")
    if not (0.0 <= alpha <= 1.0):
        raise ValueError(f"Alpha must be between 0.0 and 1.0, current alpha is {alpha}")

    self.temperature = float(temperature)
    self.alpha = float(alpha)
    self.kl_div = nn.KLDivLoss(reduction="batchmean")
    self.cross_entropy = nn.CrossEntropyLoss()
forward 
forward(
    student_outputs: Tensor,
    teacher_outputs: Tensor,
    labels: Tensor | None = None,
) -> torch.Tensor

Computes combined Cross-Entropy and KD divergence losses.

Parameters:

Name Type Description Default
student_outputs Tensor

Raw unnormalized logits from the student model (Shape: [B, C]).

 required
teacher_outputs Tensor

Raw unnormalized logits from the teacher model (Shape: [B, C]).

 required
labels Tensor | None

Ground-truth class indices (Shape: [B]). Optional if alpha == 1.0.

 None

Returns:

Type Description
Tensor

torch.Tensor: Weighted scalar loss value.

Raises:

Type Description
ValueError

If labels is None when alpha < 1.0.
ValueError

If shapes of student_outputs and teacher_outputs mismatch.
Source code in src/shrinkai/distillation/losses/logits.py 
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
@expects_logits
def forward(
    self,
    student_outputs: torch.Tensor,
    teacher_outputs: torch.Tensor,
    labels: torch.Tensor | None = None,
) -> torch.Tensor:
    """Computes combined Cross-Entropy and KD divergence losses.

    Args:
        student_outputs: Raw unnormalized logits from the student model (Shape: [B, C]).
        teacher_outputs: Raw unnormalized logits from the teacher model (Shape: [B, C]).
        labels: Ground-truth class indices (Shape: [B]). Optional if alpha == 1.0.

    Returns:
        torch.Tensor: Weighted scalar loss value.

    Raises:
        ValueError: If `labels` is None when `alpha` < 1.0.
        ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
    """
    if student_outputs.shape != teacher_outputs.shape:
        raise ValueError(
            f"Shape mismatch: student logits {student_outputs.shape} "
            f"vs teacher logits {teacher_outputs.shape}"
        )

    soft_student = F.log_softmax(student_outputs / self.temperature, dim=-1)
    soft_teacher = F.softmax(teacher_outputs / self.temperature, dim=-1)
    kd_loss = self.kl_div(soft_student, soft_teacher) * (self.temperature**2)

    if self.alpha == 1.0:
        return kd_loss

    if labels is None:
        raise ValueError("Ground-truth `labels` are required when `alpha` < 1.0.")

    ce_loss = self.cross_entropy(student_outputs, labels)
    return (1.0 - self.alpha) * ce_loss + self.alpha * kd_loss

JSDLoss

Bases: BaseDistillationLoss

Jensen-Shannon Divergence (JSD) loss for Knowledge Distillation.

JSD is a symmetric and bounded alternative to the standard KL Divergence. It computes the divergence of both distributions from their average distribution M. This boundedness prevents gradient explosion, especially early in training when the student's predictions might diverge heavily from the teacher's.

Equation
\[ \begin{aligned} M &= 0.5 \cdot (P_{student} + P_{teacher}) \\ L_{JSD} &= 0.5 \cdot \text{KL}(P_{student} \parallel M) + 0.5 \cdot \text{KL}(P_{teacher} \parallel M) \end{aligned} \]

Attributes:

Name Type Description
temperature float

Softening factor for logits. Must be > 0.

Methods:

Name Description
__init__

Initializes the JSDLoss module.
forward

Computes the JSD between softened student and teacher distributions.
Source code in src/shrinkai/distillation/losses/logits.py 
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
class JSDLoss(BaseDistillationLoss):
    r"""Jensen-Shannon Divergence (JSD) loss for Knowledge Distillation.

    JSD is a symmetric and bounded alternative to the standard KL Divergence.
    It computes the divergence of both distributions from their average distribution M.
    This boundedness prevents gradient explosion, especially early in training when
    the student's predictions might diverge heavily from the teacher's.

    Equation:
        $$
        \begin{aligned}
        M &= 0.5 \cdot (P_{student} + P_{teacher}) \\
        L_{JSD} &= 0.5 \cdot \text{KL}(P_{student} \parallel M) + 0.5 \cdot \text{KL}(P_{teacher} \parallel M)
        \end{aligned}
        $$

    Attributes:
        temperature (float): Softening factor for logits. Must be > 0.
    """  # noqa: E501

    def __init__(self, temperature: float = 4.0) -> None:
        """Initializes the JSDLoss module.

        Args:
            temperature: Softening factor for logits (T > 0). Defaults to 4.0.

        Raises:
            ValueError: If `temperature` <= 0.
        """
        super().__init__()
        if temperature <= 0:
            raise ValueError(f"Temperature must be positive, got {temperature}")

        self.temperature = float(temperature)
        self.kl_div = nn.KLDivLoss(reduction="batchmean")

    @expects_logits
    def forward(
        self,
        student_outputs: torch.Tensor,
        teacher_outputs: torch.Tensor,
        labels: torch.Tensor | None = None,
    ) -> torch.Tensor:
        """Computes the JSD between softened student and teacher distributions.

         Args:
            student_outputs: Raw unnormalized logits from the student model (Shape: [B, C] or [B, S, C]).
            teacher_outputs: Raw unnormalized logits from the teacher model (Shape: [B, C] or [B, S, C]).
            labels: Ground-truth labels (ignored, kept for API compatibility).

        Returns:
            torch.Tensor: Scalar loss value.

        Raises:
            ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
        """  # noqa: E501
        if student_outputs.shape != teacher_outputs.shape:
            raise ValueError("Shape mismatch between student and teacher logits.")

        p_s = F.softmax(student_outputs / self.temperature, dim=-1)
        p_t = F.softmax(teacher_outputs / self.temperature, dim=-1)

        m = 0.5 * (p_s + p_t)

        log_m = torch.log(m.clamp(min=1e-8))
        kl_s_m = self.kl_div(input=log_m, target=p_s)
        kl_t_m = self.kl_div(input=log_m, target=p_t)

        jsd = 0.5 * (kl_s_m + kl_t_m)

        return jsd * (self.temperature**2)
Methods:
__init__ 
__init__(temperature: float = 4.0) -> None

Initializes the JSDLoss module.

Parameters:

Name Type Description Default
temperature float

Softening factor for logits (T > 0). Defaults to 4.0.

 4.0

Raises:

Type Description
ValueError

If temperature <= 0.
Source code in src/shrinkai/distillation/losses/logits.py 
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
def __init__(self, temperature: float = 4.0) -> None:
    """Initializes the JSDLoss module.

    Args:
        temperature: Softening factor for logits (T > 0). Defaults to 4.0.

    Raises:
        ValueError: If `temperature` <= 0.
    """
    super().__init__()
    if temperature <= 0:
        raise ValueError(f"Temperature must be positive, got {temperature}")

    self.temperature = float(temperature)
    self.kl_div = nn.KLDivLoss(reduction="batchmean")
forward 
forward(
    student_outputs: Tensor,
    teacher_outputs: Tensor,
    labels: Tensor | None = None,
) -> torch.Tensor

Computes the JSD between softened student and teacher distributions.

Args: student_outputs: Raw unnormalized logits from the student model (Shape: [B, C] or [B, S, C]). teacher_outputs: Raw unnormalized logits from the teacher model (Shape: [B, C] or [B, S, C]). labels: Ground-truth labels (ignored, kept for API compatibility).

Returns:

Type Description
Tensor

torch.Tensor: Scalar loss value.

Raises:

Type Description
ValueError

If shapes of student_outputs and teacher_outputs mismatch.
Source code in src/shrinkai/distillation/losses/logits.py 
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
@expects_logits
def forward(
    self,
    student_outputs: torch.Tensor,
    teacher_outputs: torch.Tensor,
    labels: torch.Tensor | None = None,
) -> torch.Tensor:
    """Computes the JSD between softened student and teacher distributions.

     Args:
        student_outputs: Raw unnormalized logits from the student model (Shape: [B, C] or [B, S, C]).
        teacher_outputs: Raw unnormalized logits from the teacher model (Shape: [B, C] or [B, S, C]).
        labels: Ground-truth labels (ignored, kept for API compatibility).

    Returns:
        torch.Tensor: Scalar loss value.

    Raises:
        ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
    """  # noqa: E501
    if student_outputs.shape != teacher_outputs.shape:
        raise ValueError("Shape mismatch between student and teacher logits.")

    p_s = F.softmax(student_outputs / self.temperature, dim=-1)
    p_t = F.softmax(teacher_outputs / self.temperature, dim=-1)

    m = 0.5 * (p_s + p_t)

    log_m = torch.log(m.clamp(min=1e-8))
    kl_s_m = self.kl_div(input=log_m, target=p_s)
    kl_t_m = self.kl_div(input=log_m, target=p_t)

    jsd = 0.5 * (kl_s_m + kl_t_m)

    return jsd * (self.temperature**2)

PureKDLoss

Bases: HintonLoss

Pure Knowledge Distillation loss.

Implement distillation loss (Kullback-Leibler divergence on softened probabilities produced by a teacher model at a given temperature). In fact, a PureKDLossobject is just a HintonLoss object with alpha set to 1.

Equation
\[L = T^2 \cdot L_{kl}\left(\text{softmax}\left(\frac{z_s}{T}\right), \text{softmax}\left(\frac{z_t}{T}\right)\right)\]

Attributes:

Name Type Description
temperature float

Softening factor for logits. Higher values produce smoother probability distributions over classes. Must be > 0.

Methods:

Name Description
__init__

Initializes the PureKDLoss module.
Source code in src/shrinkai/distillation/losses/logits.py 
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
class PureKDLoss(HintonLoss):
    r"""Pure Knowledge Distillation loss.

    Implement distillation loss (Kullback-Leibler divergence on softened probabilities
    produced by a teacher model at a given temperature). In fact, a `PureKDLoss`object
    is just a `HintonLoss` object with `alpha` set to 1.

    Equation:
        $$L = T^2 \cdot L_{kl}\left(\text{softmax}\left(\frac{z_s}{T}\right), \text{softmax}\left(\frac{z_t}{T}\right)\right)$$

    Attributes:
        temperature (float): Softening factor for logits. Higher values produce
            smoother probability distributions over classes. Must be > 0.
    """  # noqa: E501

    def __init__(self, temperature: float = 4.0) -> None:
        """Initializes the PureKDLoss module.

        Args:
            temperature: Temperature scaling factor (T > 0). Defaults to 4.0.

        Raises:
            ValueError: If `temperature` <= 0.
        """
        super().__init__(temperature=temperature, alpha=1.0)
Methods:
__init__ 
__init__(temperature: float = 4.0) -> None

Initializes the PureKDLoss module.

Parameters:

Name Type Description Default
temperature float

Temperature scaling factor (T > 0). Defaults to 4.0.

 4.0

Raises:

Type Description
ValueError

If temperature <= 0.
Source code in src/shrinkai/distillation/losses/logits.py 
141
142
143
144
145
146
147
148
149
150
def __init__(self, temperature: float = 4.0) -> None:
    """Initializes the PureKDLoss module.

    Args:
        temperature: Temperature scaling factor (T > 0). Defaults to 4.0.

    Raises:
        ValueError: If `temperature` <= 0.
    """
    super().__init__(temperature=temperature, alpha=1.0)

ReverseKLLoss

Bases: BaseDistillationLoss

Reverse Kullback-Leibler divergence for Knowledge Distillation (Gu et al. (2024), MiniLLM).

Standard KD (Forward KL) computes KL(P_teacher || P_student), which is "mode-covering". Reverse KL computes KL(P_student || P_teacher), which is "mode-seeking".

For Large Language Models (LLMs), Reverse KL is highly effective because it strongly penalizes the student for assigning high probabilities to tokens that the teacher considers unlikely, thereby reducing hallucinations and degeneration.

Equation
\[L = T^2 \cdot \sum \left( P_s \cdot (\log(P_s) - \log(P_t)) \right)\]

Attributes:

Name Type Description
temperature float

Softening factor for logits. Must be > 0. Note: In LLM distillation, temperature is often set close to 1.0.

Methods:

Name Description
__init__

Initializes the ReverseKLLoss module.
forward

Computes the Reverse KL divergence loss.
Source code in src/shrinkai/distillation/losses/logits.py 
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
class ReverseKLLoss(BaseDistillationLoss):
    r"""Reverse Kullback-Leibler divergence for Knowledge Distillation (Gu et al. (2024),
    MiniLLM).

    Standard KD (Forward KL) computes KL(P_teacher || P_student), which is "mode-covering".
    Reverse KL computes KL(P_student || P_teacher), which is "mode-seeking".

    For Large Language Models (LLMs), Reverse KL is highly effective because it strongly
    penalizes the student for assigning high probabilities to tokens that the teacher
    considers unlikely, thereby reducing hallucinations and degeneration.

    Equation:
        $$L = T^2 \cdot \sum \left( P_s \cdot (\log(P_s) - \log(P_t)) \right)$$

    Attributes:
        temperature (float): Softening factor for logits. Must be > 0.
            Note: In LLM distillation, temperature is often set close to 1.0.
    """  # noqa: E501

    def __init__(self, temperature: float = 1.0) -> None:
        """Initializes the ReverseKLLoss module.

        Args:
            temperature: Temperature scaling factor (T > 0). Defaults to 1.0.

        Raises:
            ValueError: If `temperature` <= 0.
        """
        super().__init__()

        if temperature <= 0:
            raise ValueError(f"Temperature must be positive, current temperature is {temperature}")

        self.temperature = float(temperature)
        self.kl_div = nn.KLDivLoss(reduction="batchmean", log_target=True)

    @expects_logits
    def forward(
        self,
        student_outputs: torch.Tensor,
        teacher_outputs: torch.Tensor,
        labels: torch.Tensor | None = None,
    ) -> torch.Tensor:
        """Computes the Reverse KL divergence loss.

        Args:
            student_outputs: Raw unnormalized logits from the student model
                (Shape: [B, C] or [B, S, C]).
            teacher_outputs: Raw unnormalized logits from the teacher model
                (Shape: [B, C] or [B, S, C]).
            labels: Ground-truth labels (ignored, kept for API compatibility).

        Returns:
            torch.Tensor: Scalar loss value.

        Raises:
            ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
        """
        if student_outputs.shape != teacher_outputs.shape:
            raise ValueError(
                f"Shape mismatch: student logits {student_outputs.shape} "
                f"vs teacher logits {teacher_outputs.shape}"
            )

        # IMPORTANT: Do not swap `input` and `target`!
        # PyTorch's KLDivLoss computes KL(target || input).
        # Standard KD (Forward KL) passes `target=teacher, input=student` -> KL(teacher || student).
        # For Reverse KL, we want KL(student || teacher), so we MUST pass:
        # `target=student, input=teacher`.
        log_soft_student = F.log_softmax(student_outputs / self.temperature, dim=-1)
        log_soft_teacher = F.log_softmax(teacher_outputs / self.temperature, dim=-1)
        kd_loss = self.kl_div(input=log_soft_teacher, target=log_soft_student)
        return kd_loss * (self.temperature**2)
Methods:
__init__ 
__init__(temperature: float = 1.0) -> None

Initializes the ReverseKLLoss module.

Parameters:

Name Type Description Default
temperature float

Temperature scaling factor (T > 0). Defaults to 1.0.

 1.0

Raises:

Type Description
ValueError

If temperature <= 0.
Source code in src/shrinkai/distillation/losses/logits.py 
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
def __init__(self, temperature: float = 1.0) -> None:
    """Initializes the ReverseKLLoss module.

    Args:
        temperature: Temperature scaling factor (T > 0). Defaults to 1.0.

    Raises:
        ValueError: If `temperature` <= 0.
    """
    super().__init__()

    if temperature <= 0:
        raise ValueError(f"Temperature must be positive, current temperature is {temperature}")

    self.temperature = float(temperature)
    self.kl_div = nn.KLDivLoss(reduction="batchmean", log_target=True)
forward 
forward(
    student_outputs: Tensor,
    teacher_outputs: Tensor,
    labels: Tensor | None = None,
) -> torch.Tensor

Computes the Reverse KL divergence loss.

Parameters:

Name Type Description Default
student_outputs Tensor

Raw unnormalized logits from the student model (Shape: [B, C] or [B, S, C]).

 required
teacher_outputs Tensor

Raw unnormalized logits from the teacher model (Shape: [B, C] or [B, S, C]).

 required
labels Tensor | None

Ground-truth labels (ignored, kept for API compatibility).

 None

Returns:

Type Description
Tensor

torch.Tensor: Scalar loss value.

Raises:

Type Description
ValueError

If shapes of student_outputs and teacher_outputs mismatch.
Source code in src/shrinkai/distillation/losses/logits.py 
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
@expects_logits
def forward(
    self,
    student_outputs: torch.Tensor,
    teacher_outputs: torch.Tensor,
    labels: torch.Tensor | None = None,
) -> torch.Tensor:
    """Computes the Reverse KL divergence loss.

    Args:
        student_outputs: Raw unnormalized logits from the student model
            (Shape: [B, C] or [B, S, C]).
        teacher_outputs: Raw unnormalized logits from the teacher model
            (Shape: [B, C] or [B, S, C]).
        labels: Ground-truth labels (ignored, kept for API compatibility).

    Returns:
        torch.Tensor: Scalar loss value.

    Raises:
        ValueError: If shapes of `student_outputs` and `teacher_outputs` mismatch.
    """
    if student_outputs.shape != teacher_outputs.shape:
        raise ValueError(
            f"Shape mismatch: student logits {student_outputs.shape} "
            f"vs teacher logits {teacher_outputs.shape}"
        )

    # IMPORTANT: Do not swap `input` and `target`!
    # PyTorch's KLDivLoss computes KL(target || input).
    # Standard KD (Forward KL) passes `target=teacher, input=student` -> KL(teacher || student).
    # For Reverse KL, we want KL(student || teacher), so we MUST pass:
    # `target=student, input=teacher`.
    log_soft_student = F.log_softmax(student_outputs / self.temperature, dim=-1)
    log_soft_teacher = F.log_softmax(teacher_outputs / self.temperature, dim=-1)
    kd_loss = self.kl_div(input=log_soft_teacher, target=log_soft_student)
    return kd_loss * (self.temperature**2)

Functions:

expects_logits 

expects_logits(func)

Decorator to automatically extract logits from FeatureExtractor tuples.

Source code in src/shrinkai/distillation/losses/logits.py 
34
35
36
37
38
39
40
41
42
43
def expects_logits(func):
    """Decorator to automatically extract logits from FeatureExtractor tuples."""

    @wraps(func)
    def wrapper(self, student_outputs, teacher_outputs, *args, **kwargs):
        s_logits = student_outputs[0] if isinstance(student_outputs, tuple) else student_outputs
        t_logits = teacher_outputs[0] if isinstance(teacher_outputs, tuple) else teacher_outputs
        return func(self, s_logits, t_logits, *args, **kwargs)

    return wrapper