{"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/exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","arxiv_id":"2004.03829","date":"2020-04-08","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Zhaojiang Lin","Andrea Madotto","Pascale Fung"],"abstract":"Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power scenarios (e.g., mobile). In this paper, we propose an effective way to fine-tune multiple down-stream generation tasks simultaneously using a single, large pre-trained model. The experiments on five diverse language generation tasks show that by just using an additional 2-3% parameters for each task, our model can maintain or even improve the performance of fine-tuning the whole model.","url_abs":"https://arxiv.org/abs/2004.03829v2","url_pdf":"https://arxiv.org/pdf/2004.03829v2.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":"exploring-versatile-generative-language-model","repo_url":"https://github.com/zlinao/VGLM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.03829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.03829"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zlinao/VGLM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_honours":1,"ran":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"0f786c407fb1ee4c","entry":"swish","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"35ef111fc00c21b4","entry":"build_tf_to_pytorch_map","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_transfo_xl.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35ef111fc00c21b4"}},{"code_sha256_prefix":"8d23fbe2b99b840b","entry":"gelu","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_gpt2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"69c6d14de8190cfb","entry":"gelu","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_distilbert.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_distilbert.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"code_sha256_prefix":"0c145728a35789fa","entry":"load_tf_weights_in_bert","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_bert.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c145728a35789fa"}},{"code_sha256_prefix":"93228a3eb5c4d179","entry":"sample_logits","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_transfo_xl_utilities.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"code_sha256_prefix":"695eaa24be6f2a1d","entry":"top_filtering","repo":"zlinao/VGLM","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"695eaa24be6f2a1d"}},{"code_sha256_prefix":"654e91efc679fe84","entry":"load_tf_weights_in_gpt2","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_gpt2.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_gpt2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"654e91efc679fe84"}},{"code_sha256_prefix":"42ee168c3ae12e60","entry":"load_tf_weights_in_openai_gpt","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_openai.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42ee168c3ae12e60"}},{"code_sha256_prefix":"23d246e59ef9447b","entry":"load_tf_weights_in_transfo_xl","repo":"zlinao/VGLM","repo_kind":"official","path":"pytorch_transformers/modeling_transfo_xl.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_transfo_xl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23d246e59ef9447b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}