An identity intervention that keeps the hidden states it sees and adds a gradient to the one flowing back through it: the way to train a CausalLM on a loss of a layer's output.
More...
|
| | HiddenStateTap (DeviceBackend *backend) |
| |
| Tensor | forward_at (const Tensor &hidden, int64_t start, int64_t prompt_length) override |
| | The edit for hidden states covering positions [start, start + L) of a sequence whose prompt is prompt_length positions long. forward(x) is forward_at(x, 0, L). Cached generation calls it once on the prompt and then once per new token, each a later start.
|
| |
| Tensor | backward (const Tensor &grad_output) override |
| | grad_output plus the gradient given to add_gradient(), if any, which is then dropped.
|
| |
| Tensor | propagate_relevance (const Tensor &relevance_out, const LRPRuleConfig &config) override |
| | Computes this module's contribution to LRP relevance propagation.
|
| |
| bool | supports_lrp_rule (LRPRule) const override |
| | Whether propagate_relevance() implements rule (no silent fallback: callers such as ExplainerContext::relevance_pass() throw rather than run a module on a rule it does not implement).
|
| |
| OpType | op_type () const override |
| | This module's operation-category tag, for ComputationGraph node tagging.
|
| |
| std::optional< DeviceType > | compute_device () const override |
| | The device this module computes on, so forward() can reject an input on another device before any kernel sees it (roadmap FND-8).
|
| |
| void | release_activations () override |
| | Frees the tensors forward() kept for backward() and the relevance passes; containers release their children too. Inference that only needs the output calls it after each forward, so a deep model holds one layer's activations at a time (a 1024-token ESM-2 650M pass otherwise keeps over 10 GB of them).
|
| |
| const Tensor & | hidden () const |
| | The last forward()'s hidden states, (N, L, hidden_size).
|
| |
| void | add_gradient (const Tensor &gradient) |
| | A gradient for the next backward() to add, the hidden states' shape.
|
| |
| virtual | ~Module ()=default |
| |
| Tensor | forward (const Tensor &input) |
| | Runs this module's forward computation.
|
| |
| std::pair< Tensor, NodeId > | forward_traced (const Tensor &input, NodeId input_node, ComputationGraph &graph, Autograd &autograd) |
| | Runs forward() while also registering a ComputationGraph node (tagged with this module's op_type(), parented to input_node) and wiring an Autograd backward function that reuses this module's own backward() – the opt-in traced/explainable path, per Phase 2 Mission 0.
|
| |
| virtual std::vector< NamedParamRef > | named_parameters () |
| | This module's trainable parameters, each with its hierarchical name – the one place a module declares its parameters (roadmap FND-1).
|
| |
| virtual std::vector< NamedBufferRef > | named_buffers () |
| | This module's buffers: state a checkpoint must save that no optimizer updates.
|
| |
| virtual std::vector< NamedModuleRef > | named_children () |
| | This module's direct sub-modules, each under the prefix its parameters carry in named_parameters(), in the same order (TRN-7: how ApplyLora() finds a model's Linear layers). Default: none. NamedModules() walks the whole tree.
|
| |
| virtual std::vector< ParamRef > | parameters () |
| | This module's trainable parameters and their gradients, for an optimizer to update uniformly across module types.
|
| |
| void | set_requires_grad (bool requires_grad, const std::string &prefix="") |
| | Freezes (false) or unfreezes (true) parameters by name (roadmap FND-2).
|
| |
| virtual void | set_training (bool training) |
| | Sets this module's training/eval mode. Defaults to training (matches every mainstream framework's Module default).
|
| |
| bool | is_training () const |
| | Whether this module is currently in training mode.
|
| |
An identity intervention that keeps the hidden states it sees and adds a gradient to the one flowing back through it: the way to train a CausalLM on a loss of a layer's output.
- Note
- Each forward() replaces the kept states; add_gradient() applies to the next backward() only. Relevance passes through unchanged.