{"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/lora-land-310-fine-tuned-llms-that-rival-gpt","title":"LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report","arxiv_id":"2405.00732","date":"2024-04-29","proceeding":null,"authors":["Justin Zhao","Timothy Wang","Wael Abid","Geoffrey Angus","Arnav Garg","Jeffery Kinnison","Alex Sherstinsky","Piero Molino","Travis Addair","Devvret Rishi"],"abstract":"Low Rank Adaptation (LoRA) has emerged as one of the most widely adopted methods for Parameter Efficient Fine-Tuning (PEFT) of Large Language Models (LLMs). LoRA reduces the number of trainable parameters and memory usage while achieving comparable performance to full fine-tuning. We aim to assess the viability of training and serving LLMs fine-tuned with LoRA in real-world applications. First, we measure the quality of LLMs fine-tuned with quantized low rank adapters across 10 base models and 31 tasks for a total of 310 models. We find that 4-bit LoRA fine-tuned models outperform base models by 34 points and GPT-4 by 10 points on average. Second, we investigate the most effective base models for fine-tuning and assess the correlative and predictive capacities of task complexity heuristics in forecasting the outcomes of fine-tuning. Finally, we evaluate the latency and concurrency capabilities of LoRAX, an open-source Multi-LoRA inference server that facilitates the deployment of multiple LoRA fine-tuned models on a single GPU using shared base model weights and dynamic adapter loading. LoRAX powers LoRA Land, a web application that hosts 25 LoRA fine-tuned Mistral-7B LLMs on a single NVIDIA A100 GPU with 80GB memory. LoRA Land highlights the quality and cost-effectiveness of employing multiple specialized LLMs over a single, general-purpose LLM.","url_abs":"https://arxiv.org/abs/2405.00732v1","url_pdf":"https://arxiv.org/pdf/2405.00732v1.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":"lora-land-310-fine-tuned-llms-that-rival-gpt","repo_url":"https://github.com/predibase/lora_bakeoff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.00732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00732"}},"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/predibase/lora_bakeoff","reach":{"status":"ok"}}],"summary":{"ran":11,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"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":12,"samples":[{"code_sha256_prefix":"84ce7087a182be43","entry":"add_collected_tags","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"tasks/bc5cdr/preprocessing.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/tasks/bc5cdr/preprocessing.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":"84ce7087a182be43"}},{"code_sha256_prefix":"772654a542abfa4b","entry":"add_preprocessed_columns","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"tasks/bc5cdr/preprocessing.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/tasks/bc5cdr/preprocessing.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":"772654a542abfa4b"}},{"code_sha256_prefix":"73b3742ba8c17bb6","entry":"add_realized_prompt","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"tasks/arc_combined/preprocessing.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/tasks/arc_combined/preprocessing.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":"73b3742ba8c17bb6"}},{"code_sha256_prefix":"525c4edd969630e7","entry":"filter_on_split","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"utils/dataset_loading.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/utils/dataset_loading.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":"525c4edd969630e7"}},{"code_sha256_prefix":"e99446edd24636a6","entry":"get_accuracy","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"utils/metric_fns.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/utils/metric_fns.py","link_basis":"first_harvest_node","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":"e99446edd24636a6"}},{"code_sha256_prefix":"6afeacd61635830c","entry":"get_binary_accuracy_flex","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"utils/metric_fns.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/utils/metric_fns.py","link_basis":"first_harvest_node","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":"6afeacd61635830c"}},{"code_sha256_prefix":"651a91eb0cd11080","entry":"get_bool_value_from_text","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"utils/metric_fns.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/utils/metric_fns.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":"651a91eb0cd11080"}},{"code_sha256_prefix":"69e611fa0193f59a","entry":"get_dataframe_from_local_file","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"utils/dataset_loading.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/utils/dataset_loading.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":"69e611fa0193f59a"}},{"code_sha256_prefix":"a765d247ae477053","entry":"get_pbase_response","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"parse_responses.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/parse_responses.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":"a765d247ae477053"}},{"code_sha256_prefix":"5ee1ae69847feee9","entry":"get_processed_df","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"tasks/arc_combined/preprocessing.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/tasks/arc_combined/preprocessing.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":"5ee1ae69847feee9"}},{"code_sha256_prefix":"ee80c46fc38cca58","entry":"get_realized_prompt","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"tasks/arc_combined/preprocessing.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/tasks/arc_combined/preprocessing.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":"ee80c46fc38cca58"}},{"code_sha256_prefix":"c469092586a8fdac","entry":"get_metadata_for_task","repo":"predibase/lora_bakeoff","repo_kind":"official","path":"utils/task_metadata.py","file_url":"https://github.com/predibase/lora_bakeoff/blob/HEAD/utils/task_metadata.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":"c469092586a8fdac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}