【开源实习】- Dora-finetuning模型微调 - #IAN239 #1620
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lvyufeng
reviewed
Sep 5, 2024
mindnlp/peft/tuners/lora/dora.py
Outdated
| from mindnlp.peft.utils.integrations import dequantize_module_weight | ||
| from ...utils.other import transpose | ||
| import mindspore | ||
| from mindspore import ops |
mindnlp/peft/utils/integrations.py
Outdated
| from mindspore import Parameter | ||
| from mindnlp.core import ops | ||
|
|
||
| def dequantize_module_weight(module: nn.Module) -> nn.Parameter: |
lvyufeng
reviewed
Sep 9, 2024
requirements/requirements.txt
Outdated
| tiktoken | ||
| faiss_cpu | ||
| phonemizer | ||
| bitsandbytes |
lvyufeng
reviewed
Sep 9, 2024
mindnlp/peft/tuners/lora/dora.py
Outdated
| lora_weight = lora_weight.half() | ||
| weight_norm = self.get_weight_norm(weight, lora_weight, scaling) | ||
| if place_on_cpu: | ||
| weight_norm = weight_norm.to("cpu") |
lvyufeng
reviewed
Sep 9, 2024
| self._disable_adapters = False | ||
| self.merged_adapters = [] | ||
| self.use_dora: dict[str, bool] = {} | ||
| self.lora_magnitude_vector: Optional[ParameterDict] = None # for DoRA |
lvyufeng
reviewed
Sep 9, 2024
| # initialize a the same way as the default for nn.Linear and b to zero | ||
| nn.init.zeros_(self.lora_embedding_A[adapter_name]) | ||
| nn.init.normal_(self.lora_embedding_B[adapter_name]) | ||
| def dora_init(self, adapter_name: str) -> None: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.