{"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/meteora-multiple-tasks-embedded-lora-for","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","arxiv_id":"2405.13053","date":"2024-05-19","proceeding":null,"authors":["Jingwei Xu","Junyu Lai","Yunpeng Huang"],"abstract":"The pretrain+fine-tune paradigm is foundational for deploying large language models (LLMs) across various downstream applications. Within this framework, Low-Rank Adaptation (LoRA) stands out for its parameter-efficient fine-tuning (PEFT), producing numerous reusable task-specific LoRA adapters. However, this approach requires explicit task intention selection, posing challenges for autonomous task sensing and switching during inference with multiple existing LoRA adapters embedded in a single LLM. In this work, we introduce MeteoRA (Multiple-tasks embedded LoRA), a scalable and efficient framework that reuses multiple task-specific LoRA adapters into the base LLM via a full-mode Mixture-of-Experts (MoE) architecture. This framework also includes novel MoE forward acceleration strategies to address the efficiency challenges of traditional MoE implementations. Our evaluation, using the LlaMA2-13B and LlaMA3-8B base models equipped with 28 existing LoRA adapters through MeteoRA, demonstrates equivalent performance with the traditional PEFT method. Moreover, the LLM equipped with MeteoRA achieves superior performance in handling composite tasks, effectively solving ten sequential problems in a single inference pass, thereby demonstrating the framework's enhanced capability for timely adapter switching.","url_abs":"https://arxiv.org/abs/2405.13053v3","url_pdf":"https://arxiv.org/pdf/2405.13053v3.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":"meteora-multiple-tasks-embedded-lora-for","repo_url":"https://github.com/paragonlight/meteor-of-lora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.13053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13053"}},"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/paragonlight/meteor-of-lora","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_honours":3,"ran":2,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":10,"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":10,"samples":[{"code_sha256_prefix":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/modeling_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_llama_meteor.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d61c483a3c2b3156"}},{"code_sha256_prefix":"a1b46b3f84e76f6a","entry":"apply_rotary_pos_emb","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/modeling_flax_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_flax_llama_meteor.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a1b46b3f84e76f6a"}},{"code_sha256_prefix":"507f475feb734647","entry":"compute_intermediate_size","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/convert_llama_meteor_weights_to_hf.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/convert_llama_meteor_weights_to_hf.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"507f475feb734647"}},{"code_sha256_prefix":"660ecba66bbbf2c0","entry":"create_sinusoidal_positions","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/modeling_flax_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_flax_llama_meteor.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"660ecba66bbbf2c0"}},{"code_sha256_prefix":"0aac389c4e4474f4","entry":"get_task_path","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"eval_model.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/eval_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0aac389c4e4474f4"}},{"code_sha256_prefix":"c5bcf01d18bba63d","entry":"read_json","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/convert_llama_meteor_weights_to_hf.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/convert_llama_meteor_weights_to_hf.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c5bcf01d18bba63d"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/modeling_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_llama_meteor.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"6b3f1075d5cc01c4","entry":"rotate_half","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/modeling_flax_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_flax_llama_meteor.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6b3f1075d5cc01c4"}},{"code_sha256_prefix":"cc6c9f9c9d5bd68f","entry":"lora_gate_loss_func","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/modeling_llama_meteor.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/modeling_llama_meteor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cc6c9f9c9d5bd68f"}},{"code_sha256_prefix":"b91ba72f3b013e76","entry":"write_model","repo":"paragonlight/meteor-of-lora","repo_kind":"official","path":"base_model/llama/convert_llama_meteor_weights_to_hf.py","file_url":"https://github.com/paragonlight/meteor-of-lora/blob/HEAD/base_model/llama/convert_llama_meteor_weights_to_hf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b91ba72f3b013e76"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}