{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/code-llama-open-foundation-models-for-code","title":"Code Llama: Open Foundation Models for Code","arxiv_id":"2308.12950","date":"2023-08-24","proceeding":null,"authors":["Baptiste Rozière","Jonas Gehring","Fabian Gloeckle","Sten Sootla","Itai Gat","Xiaoqing Ellen Tan","Yossi Adi","Jingyu Liu","Romain Sauvestre","Tal Remez","Jérémy Rapin","Artyom Kozhevnikov","Ivan Evtimov","Joanna Bitton","Manish Bhatt","Cristian Canton Ferrer","Aaron Grattafiori","Wenhan Xiong","Alexandre Défossez","Jade Copet","Faisal Azhar","Hugo Touvron","Louis Martin","Nicolas Usunier","Thomas Scialom","Gabriel Synnaeve"],"abstract":"We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks. We provide multiple flavors to cover a wide range of applications: foundation models (Code Llama), Python specializations (Code Llama - Python), and instruction-following models (Code Llama - Instruct) with 7B, 13B, 34B and 70B parameters each. All models are trained on sequences of 16k tokens and show improvements on inputs with up to 100k tokens. 7B, 13B and 70B Code Llama and Code Llama - Instruct variants support infilling based on surrounding content. Code Llama reaches state-of-the-art performance among open models on several code benchmarks, with scores of up to 67% and 65% on HumanEval and MBPP, respectively. Notably, Code Llama - Python 7B outperforms Llama 2 70B on HumanEval and MBPP, and all our models outperform every other publicly available model on MultiPL-E. We release Code Llama under a permissive license that allows for both research and commercial use.","url_abs":"https://arxiv.org/abs/2308.12950v3","url_pdf":"https://arxiv.org/pdf/2308.12950v3.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":"code-llama-open-foundation-models-for-code","repo_url":"https://github.com/facebookresearch/codellama","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"code-llama-open-foundation-models-for-code","repo_url":"https://github.com/BohdanPetryshyn/code-llama-fim-fine-tuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"16k","task_name":"16k"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"humaneval","task_name":"HumanEval"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":null,"task_name":"mbpp"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Python 70B (3-shot)","rank_in_archive_order":40,"of":99,"metrics":{"Accuracy":"65.5"},"uses_additional_data":true},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama 70B (3-shot)","rank_in_archive_order":43,"of":99,"metrics":{"Accuracy":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Instruct 70B (3-shot)","rank_in_archive_order":44,"of":99,"metrics":{"Accuracy":"62.2"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Unnatural Code Llama 34B (3-shot)","rank_in_archive_order":47,"of":99,"metrics":{"Accuracy":"61.2"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Instruct 34B (3-shot)","rank_in_archive_order":51,"of":99,"metrics":{"Accuracy":"57"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Python 34B (3-shot)","rank_in_archive_order":52,"of":99,"metrics":{"Accuracy":"56.2"},"uses_additional_data":true},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama 34B (3-shot)","rank_in_archive_order":54,"of":99,"metrics":{"Accuracy":"55"},"uses_additional_data":true},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"GPT-3.5 Turbo","rank_in_archive_order":57,"of":99,"metrics":{"Accuracy":"52.2"},"uses_additional_data":true},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Instruct 13B (3-shot)","rank_in_archive_order":61,"of":99,"metrics":{"Accuracy":"49.4"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Python 13B (3-shot)","rank_in_archive_order":64,"of":99,"metrics":{"Accuracy":"49"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Python 7B (3-shot)","rank_in_archive_order":67,"of":99,"metrics":{"Accuracy":"47.6"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama 13B (3-shot)","rank_in_archive_order":72,"of":99,"metrics":{"Accuracy":"47"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama - Instruct 7B (3-shot)","rank_in_archive_order":77,"of":99,"metrics":{"Accuracy":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Code Llama 7B (3-shot)","rank_in_archive_order":81,"of":99,"metrics":{"Accuracy":"41.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.12950","atlas_url":"https://app.syntology.ai/?focus=2308.12950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12950"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.12950"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.12950"},"call":"get_harvested_code_for_paper(arxiv_id=\"2308.12950\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2308.12950"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.12950\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.12950"},"call":"get_concepts_for_paper(arxiv_id=\"2308.12950\")"}],"by_repo":[{"repo":"facebookresearch/codellama","kind":"official","samples":4,"ran":3,"instrument":2,"unverified":1},{"repo":"BohdanPetryshyn/code-llama-fim-fine-tuning","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2308.12950.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2308.12950.svg"},"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/BohdanPetryshyn/code-llama-fim-fine-tuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/codellama","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_violates":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"n_samples":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":4,"ran":3,"n_ran_checked":1,"n_instrument":2,"repositories":1},"listed":{"samples":1,"ran":0,"n_ran_checked":0,"n_instrument":0,"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":4,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":2,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"e93cc5b705c2eb3b","code_sha256_prefix":"e93cc5b705c2eb3b","entry":"precompute_freqs_cis","repo":"facebookresearch/codellama","repo_kind":"official","path":"llama/model.py","file_url":"https://github.com/facebookresearch/codellama/blob/HEAD/llama/model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dim:int/0/int, end:int/0/int, theta:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/precompute-freqs-cis","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, facebookresearch/codellama when it was checked","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"code_sha256":"70bf6ebaafd266c4","code_sha256_prefix":"70bf6ebaafd266c4","entry":"reshape_for_broadcast","repo":"facebookresearch/codellama","repo_kind":"official","path":"llama/model.py","file_url":"https://github.com/facebookresearch/codellama/blob/HEAD/llama/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"freqs_cis:Tensor/2/float, x:Tensor/4/float","fixture_out_type":"Tensor","retrieve_with":{"tool":"get_code","code_sha256":"70bf6ebaafd266c4"},"code_page":"/code/reshape-for-broadcast","census":{"url":"/census/reshape-for-broadcast","implementations":6,"papers":10,"distinct_outputs":1,"n_buckets":1,"bucket_key":null,"bucket_index":null,"bucket_label":null},"census_bucket_fragment":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, facebookresearch/codellama when it was checked","mcp_get_code":{"code_sha256":"70bf6ebaafd266c4"}},{"code_sha256":"8845976729f4c4ee","code_sha256_prefix":"8845976729f4c4ee","entry":"sample_top_p","repo":"facebookresearch/codellama","repo_kind":"official","path":"llama/generation.py","file_url":"https://github.com/facebookresearch/codellama/blob/HEAD/llama/generation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"probs:Tensor/2/float, p:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"8845976729f4c4ee"},"code_page":"/code/sample-top-p","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, facebookresearch/codellama when it was checked","mcp_get_code":{"code_sha256":"8845976729f4c4ee"}},{"code_sha256":"ed8b68645cfd07e0","code_sha256_prefix":"ed8b68645cfd07e0","entry":"apply_rotary_emb","repo":"facebookresearch/codellama","repo_kind":"official","path":"llama/model.py","file_url":"https://github.com/facebookresearch/codellama/blob/HEAD/llama/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/apply-rotary-emb","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, facebookresearch/codellama when it was checked","mcp_get_code":{"code_sha256":"ed8b68645cfd07e0"}},{"code_sha256":"eaff610771ed93b5","code_sha256_prefix":"eaff610771ed93b5","entry":"permute_char_level","repo":"BohdanPetryshyn/code-llama-fim-fine-tuning","repo_kind":"listed","path":"fim.py","file_url":"https://github.com/BohdanPetryshyn/code-llama-fim-fine-tuning/blob/HEAD/fim.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"eaff610771ed93b5"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b807b332143709e90c978cb336ab17ef962e4002fdb334fda17005200a188499","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}