{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/joint-fine-tuning-and-conversion-of","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","arxiv_id":"2410.06846","date":"2024-10-09","proceeding":null,"authors":["Mutian He","Philip N. Garner"],"abstract":"Architectures such as Linformer and Mamba have recently emerged as competitive linear time replacements for transformers. However, corresponding large pretrained models are often unavailable, especially in non-text domains. To remedy this, we present a Cross-Architecture Layerwise Distillation (CALD) approach that jointly converts a transformer model to a linear time substitute and fine-tunes it to a target task. We also compare several means to guide the fine-tuning to optimally retain the desired inference capability from the original model. The methods differ in their use of the target model and the trajectory of the parameters. In a series of empirical studies on language processing, language modeling, and speech processing, we show that CALD can effectively recover the result of the original model, and that the guiding strategy contributes to the result. Some reasons for the variation are suggested.","url_abs":"https://arxiv.org/abs/2410.06846v4","url_pdf":"https://arxiv.org/pdf/2410.06846v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"joint-fine-tuning-and-conversion-of","repo_url":"https://github.com/idiap/linearize-distill-pretrained-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"mamba","task_name":"Mamba"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linformer","method_name":"Linformer"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"multi-head-linear-attention","method_name":"Multi-Head Linear Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.06846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06846"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/idiap/linearize-distill-pretrained-transformers","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9fe691c72c114e96","entry":"get_audiofile","repo":"idiap/linearize-distill-pretrained-transformers","repo_kind":"official","path":"speech/dataloader.py","file_url":"https://github.com/idiap/linearize-distill-pretrained-transformers/blob/HEAD/speech/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9fe691c72c114e96"}},{"code_sha256_prefix":"360049fe861151ac","entry":"get_audiofile_spec","repo":"idiap/linearize-distill-pretrained-transformers","repo_kind":"official","path":"speech/dataloader.py","file_url":"https://github.com/idiap/linearize-distill-pretrained-transformers/blob/HEAD/speech/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"360049fe861151ac"}},{"code_sha256_prefix":"bdc61b27de6480a5","entry":"get_input_proto","repo":"idiap/linearize-distill-pretrained-transformers","repo_kind":"official","path":"speech/dataloader_hf.py","file_url":"https://github.com/idiap/linearize-distill-pretrained-transformers/blob/HEAD/speech/dataloader_hf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bdc61b27de6480a5"}},{"code_sha256_prefix":"207eb0e72f061701","entry":"preprocess_sqa5","repo":"idiap/linearize-distill-pretrained-transformers","repo_kind":"official","path":"speech/dataloader_hf.py","file_url":"https://github.com/idiap/linearize-distill-pretrained-transformers/blob/HEAD/speech/dataloader_hf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"207eb0e72f061701"}},{"code_sha256_prefix":"b6ea1d54052815d5","entry":"preprocess_voxceleb1","repo":"idiap/linearize-distill-pretrained-transformers","repo_kind":"official","path":"speech/dataloader_hf.py","file_url":"https://github.com/idiap/linearize-distill-pretrained-transformers/blob/HEAD/speech/dataloader_hf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6ea1d54052815d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}