Add gpt-oss (GptOssForCausalLM) support to model_surgery - #149
Open
eddielebelle wants to merge 1 commit into
Open
Add gpt-oss (GptOssForCausalLM) support to model_surgery#149eddielebelle wants to merge 1 commit into
eddielebelle wants to merge 1 commit into
Conversation
get_final_norm and get_transformer_layers raised NotImplementedError for GptOssForCausalLM. Add branches mapping to base_model.norm and base_model.layers (same shape as Llama/Gemma). get_unembedding_matrix already works via get_output_embeddings(). The GptOssModel import is guarded (try/except) so transformers versions before 4.55, when gpt-oss was added, still import this module cleanly (pyproject pins transformers>=4.38.1); the branches are skipped when the symbol is unavailable. Adds a mockmodel/gpt-oss-tiny fixture to random_small_model so the existing model_surgery tests cover it.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
get_final_norm and get_transformer_layers raised NotImplementedError for GptOssForCausalLM. Add branches mapping to base_model.norm and base_model.layers (same shape as Llama/Gemma). get_unembedding_matrix already works via get_output_embeddings().
The GptOssModel import is guarded (try/except) so transformers versions before 4.55, when gpt-oss was added, still import this module cleanly (pyproject pins transformers>=4.38.1); the branches are skipped when the symbol is unavailable.
Adds a mockmodel/gpt-oss-tiny fixture to random_small_model so the existing model_surgery tests cover it.