diff --git a/.gitattributes b/.gitattributes index 2259bf13b5bfa8d496ec8370e1ac810211fbd22e..a47dbe60b049cdd37da30b7382b37dee37c5b1b3 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2,3 +2,4 @@ *.parquet filter=lfs diff=lfs merge=lfs -text data/docs/*.jsonl filter=lfs diff=lfs merge=lfs -text data/qna/*.jsonl filter=lfs diff=lfs merge=lfs -text +data/commitpack/*.jsonl filter=lfs diff=lfs merge=lfs -text diff --git a/data/commitpack/c.jsonl b/data/commitpack/c.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..e8eeddb7c405ed23325f497d2e2f7c994cf1c5f2 --- /dev/null +++ b/data/commitpack/c.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a67d9aeac62e693fb782030ad7c4aa9e0d9f38a02bd2e06a438604a92628ca71 +size 21579446 diff --git a/data/commitpack/go.jsonl b/data/commitpack/go.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..80729a9db12c3da4c780af1162e1a884363fcc17 --- /dev/null +++ b/data/commitpack/go.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a65e973fcc6894a234fb382987cc25e26f053d60b032ea83540a5b36a528b8 +size 12417842 diff --git a/data/commitpack/java.jsonl b/data/commitpack/java.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..4d379bcafbb2ae4e454ae7095ae39989298e3001 --- /dev/null +++ b/data/commitpack/java.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c51a331320f4220d6053e3389485916c738fcaccfd583298b7738af834fa19b9 +size 57628439 diff --git a/data/commitpack/javascript.jsonl b/data/commitpack/javascript.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..731cf9537e5d05d98ceaa846fff546fe4ea184cd --- /dev/null +++ b/data/commitpack/javascript.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968688a1163c2dbbced0d0f9cf1dd52bc0b626c2ad9b02ff23f5700b2e277f25 +size 128001108 diff --git a/data/commitpack/multilang_commits.jsonl b/data/commitpack/multilang_commits.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..b5458323a15927168ae9f2055bd11b4883c106f5 --- /dev/null +++ b/data/commitpack/multilang_commits.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d34560e3f6f58a6ccb977e29e87327c4852a35b312d41577040b47e9b63cdf1 +size 7950812 diff --git a/data/commitpack/php.jsonl b/data/commitpack/php.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..5fb31848612ba1f59de552ab9fca1dd51545e11b --- /dev/null +++ b/data/commitpack/php.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda88bbb6483a504dcbaec36abd363eb6ae99531431fecc924d95ecdad91c691 +size 61660040 diff --git a/data/commitpack/python.jsonl b/data/commitpack/python.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..46e028777b700a9ecc205ac5e9708b07d411e6c3 --- /dev/null +++ b/data/commitpack/python.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d167da37e1058371c48e057cd8815d03700c867dd8bcf58e61420d4dcd288d73 +size 135858935 diff --git a/data/commitpack/ruby.jsonl b/data/commitpack/ruby.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..7e391a6411306387d5dbaaa877ca1c7bedf8de18 --- /dev/null +++ b/data/commitpack/ruby.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1970e1c286f98445e519b92360eac5618f29f422c56ac949623d42dccd04b1 +size 199971326 diff --git a/data/commitpack/rust.jsonl b/data/commitpack/rust.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d055fd82efe7f93f69f262a32acbcd3dc61bfe83 --- /dev/null +++ b/data/commitpack/rust.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5611f3701026acf3c43ba64da50f4f65a078e84fba56e2bf313e8f2996b0cc68 +size 7411711 diff --git a/data/commitpack/typescript.jsonl b/data/commitpack/typescript.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..33da8dfa8fc79c660821b3e0c1c691e59bdc7971 --- /dev/null +++ b/data/commitpack/typescript.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d32596844c62aa23b0e5a8811648f6f20fa07d9ab80499d66507136b844a76 +size 14620423 diff --git a/data/embeddings/combined_embeddings.parquet b/data/embeddings/combined_embeddings.parquet new file mode 100644 index 0000000000000000000000000000000000000000..edaab97f1c1d175da80d552c61569241d1eb9f0e --- /dev/null +++ b/data/embeddings/combined_embeddings.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360ec902c31623e5bf7b279a3bb0e93fdea3fa5de41144a9bb532c4eecd4fb86 +size 501475260 diff --git a/data/embeddings/doc_embeddings.parquet b/data/embeddings/doc_embeddings.parquet new file mode 100644 index 0000000000000000000000000000000000000000..6255c5540c7f6504ba977fa77a46b39b5f6eac5c --- /dev/null +++ b/data/embeddings/doc_embeddings.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86b44246e830b99ed6c179f815b44aa09512bdfadca140fd730242256312a50 +size 2383701 diff --git a/data/embeddings/real_code2lora_diffs.parquet b/data/embeddings/real_code2lora_diffs.parquet new file mode 100644 index 0000000000000000000000000000000000000000..3f952a2a0b10bd5e7279b08efcf1c63a3f4d8822 --- /dev/null +++ b/data/embeddings/real_code2lora_diffs.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3c6230672e5cc7c48ead5a2d61d17f16d9193bbc560521b35ae9569b90beb5 +size 351468741 diff --git a/data/embeddings/real_code2lora_embeddings.parquet b/data/embeddings/real_code2lora_embeddings.parquet new file mode 100644 index 0000000000000000000000000000000000000000..8be01fa8d586c388bfbdc0156642802b4049b544 --- /dev/null +++ b/data/embeddings/real_code2lora_embeddings.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4bb95fd2ef6cf4b7eba24c594c50c243e25275f3ec1ce30108cc98616f1e460 +size 284508845 diff --git a/data/qna/combined_qna.jsonl b/data/qna/combined_qna.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..19a834af6ce216c24c509310c9c72f233f1e15e1 --- /dev/null +++ b/data/qna/combined_qna.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70fdae7627a0222ecece7bc0093b776029d821cba35960d83e3eae6c7de89e7d +size 3564515579 diff --git a/data/qna/qna.jsonl b/data/qna/qna.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..60fb2f604fb73b1890c70819bdf831beb95710ff --- /dev/null +++ b/data/qna/qna.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30557ea430e4ebc5ab0a07e4606e0ba693cb8e51ef5ee9cded6d9034497faa5a +size 1454701 diff --git a/data/qna/real_code2lora_qna.jsonl b/data/qna/real_code2lora_qna.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a84d861e496eaa023214502948e987236ed4cd65 --- /dev/null +++ b/data/qna/real_code2lora_qna.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88c42e0034aa180882529a96f824fa878143ccbfd61fa1e30eed6109ceee16b +size 3563060878 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/.gitignore b/data/real_code2lora/code2lora-evo/.cache/huggingface/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f59ec20aabf5842d237244ece8c81ab184faeac1 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/.gitignore @@ -0,0 +1 @@ +* \ No newline at end of file diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/CACHEDIR.TAG b/data/real_code2lora/code2lora-evo/.cache/huggingface/CACHEDIR.TAG new file mode 100644 index 0000000000000000000000000000000000000000..2b927574f362cc41ca52cb6e863dbf47e664febb --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/CACHEDIR.TAG @@ -0,0 +1,4 @@ +Signature: 8a477f597d28d172789f06886806bc55 +# This file is a cache directory tag created by huggingface_hub. +# For information about cache directory tags, see: +# https://bford.info/cachedir/ diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/.gitattributes.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/.gitattributes.metadata new file mode 100644 index 0000000000000000000000000000000000000000..08ebcc048c8be9fc3f71bec3ba74f961f895088d --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/.gitattributes.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +bed0738c7eeb449bca98b5d2f33c89a1ee56349a +1784887206.240134 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/README.md.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f84e9e652d9034538b08ee250ec4bb9bd7c40de2 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/README.md.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +12076d4a9bd34d0eed0b624159820e7c340ac3df +1784887206.477736 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/cr_test.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/cr_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..ce2b6c7f29c3dfd869b8cb8b38e2d87ef6494c4e --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/cr_test.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +1472bd42bed51428bf1bccbedc4c494db58bc9a6fffa72fc95f95a0613de2169 +1784887250.161078 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/cr_val.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/cr_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..333bacc55dbd10dd20523eb5c67b81262e41cfaa --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/cr_val.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +f73959d38ad7d479a3b6715d96ae22a42ea89c4e9b1830e3f9354ebada98877f +1784887281.485605 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/train.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/train.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..5d7f20204e5556d807af7052a4d039af18446e0a --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/commits/train.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +6dfca1e1791fde09c1f310f2be9273b762332f28563d203a2ed7f0136cb3590b +1784887367.7020202 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/cr_test.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/cr_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..2402ec346cb4593235c5439206479afcdb4df030 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/cr_test.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +fc42611e215975824582df0da76984f6a65c3d5e29002a2b205fb5437cde907b +1784887229.2656882 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/cr_val.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/cr_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..1f8d6ca26a3a395471218167ca5190f4b9252e12 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/cr_val.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +3d76ca372ce366ab6f2b51765c9b5cbfbbfa33019b4e05d1dc05c25cacbea04f +1784887263.0436091 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/ir_test.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/ir_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..482b9803daad05f03d070051347e8945bbcb7c56 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/ir_test.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +af20fba7881a55b68efd82302b108615c6a5ae05be8e71d49c3455a7bbb124a4 +1784887233.92661 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/ir_val.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/ir_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..c4e1937560578ce3e6334e56ca28930cb20b4e75 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/ir_val.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +6b830ddb82490f1c7b6c44104cdcbcd1a8c9ca5f31d3c04af0421d2f0825c6a3 +1784887277.8217332 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/train.parquet.metadata b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/train.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..9ec0f7f7f28f487d378615d8274f3eef4c242cab --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/download/qna/train.parquet.metadata @@ -0,0 +1,3 @@ +93a9e8240b9482092ecc768b804cc62bae1e875a +519a092970f55750571c5223b1cfbcb0d36745a678cf41b48d4de6104c2a34e7 +1784887371.999535 diff --git a/data/real_code2lora/code2lora-evo/.cache/huggingface/trees/93a9e8240b9482092ecc768b804cc62bae1e875a.json b/data/real_code2lora/code2lora-evo/.cache/huggingface/trees/93a9e8240b9482092ecc768b804cc62bae1e875a.json new file mode 100644 index 0000000000000000000000000000000000000000..c5ad9e50f3c14e7a227d66b4dc0d7ad7bd62386e --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.cache/huggingface/trees/93a9e8240b9482092ecc768b804cc62bae1e875a.json @@ -0,0 +1,69 @@ +{ + "format_version": 1, + "files": { + ".gitattributes": { + "size": 2504, + "blob_id": "bed0738c7eeb449bca98b5d2f33c89a1ee56349a" + }, + "README.md": { + "size": 1735, + "blob_id": "12076d4a9bd34d0eed0b624159820e7c340ac3df" + }, + "commits/cr_test.parquet": { + "size": 68411936, + "blob_id": "1e2ac27253f7cf41412b4a38520e97531302d968", + "lfs_sha256": "1472bd42bed51428bf1bccbedc4c494db58bc9a6fffa72fc95f95a0613de2169", + "lfs_size": 68411936, + "xet_hash": "6e8f60efddd8c7caa8df21b2abec0198eb76cf6f6a455bdca73db38493870f0d" + }, + "commits/cr_val.parquet": { + "size": 88017946, + "blob_id": "75709b935d623b7edb5ccd83dc0282d1440ac580", + "lfs_sha256": "f73959d38ad7d479a3b6715d96ae22a42ea89c4e9b1830e3f9354ebada98877f", + "lfs_size": 88017946, + "xet_hash": "471f20effb87b24b7cb2f743e483c2e8d0799df56f1d33ff029e45552e31bbfb" + }, + "commits/train.parquet": { + "size": 612508015, + "blob_id": "ff02daf9b1c12e369523125b664706b7dba70169", + "lfs_sha256": "6dfca1e1791fde09c1f310f2be9273b762332f28563d203a2ed7f0136cb3590b", + "lfs_size": 612508015, + "xet_hash": "3d5479420b6a2cd17c9556b3235df14df1caacc9f75eac1e530a76f9a8d1d28a" + }, + "qna/cr_test.parquet": { + "size": 16240753, + "blob_id": "5d5e537f81519bb5fc611cffc1d2f3e6a643403d", + "lfs_sha256": "fc42611e215975824582df0da76984f6a65c3d5e29002a2b205fb5437cde907b", + "lfs_size": 16240753, + "xet_hash": "8ee16b74836d3602cf10e960cba16f083e25443e7803da5f411c9af49b3b0b12" + }, + "qna/cr_val.parquet": { + "size": 23488346, + "blob_id": "b979c9c6fc248831d906057a88aa7c123eede5b4", + "lfs_sha256": "3d76ca372ce366ab6f2b51765c9b5cbfbbfa33019b4e05d1dc05c25cacbea04f", + "lfs_size": 23488346, + "xet_hash": "a7764c559c4dda09f842dd904c11d4c7ae340c3b3d941e15fb5e6706cacec1be" + }, + "qna/ir_test.parquet": { + "size": 22805812, + "blob_id": "e997fa64278ff967d0c08c22bb9c7a5571c343d5", + "lfs_sha256": "af20fba7881a55b68efd82302b108615c6a5ae05be8e71d49c3455a7bbb124a4", + "lfs_size": 22805812, + "xet_hash": "9c268ba844d32ab694baf09c446c689289b9e873e4de8f9b9d3cae5470380450" + }, + "qna/ir_val.parquet": { + "size": 20154479, + "blob_id": "4936c3c5f14b99c30b094b696a7df5f566745ffb", + "lfs_sha256": "6b830ddb82490f1c7b6c44104cdcbcd1a8c9ca5f31d3c04af0421d2f0825c6a3", + "lfs_size": 20154479, + "xet_hash": "d51d246ad2ee31868d3a7d16890466349427120f47ef7fc278181d8e1e3d879d" + }, + "qna/train.parquet": { + "size": 135352731, + "blob_id": "647f3e27841055c9538eec4495520d63e30f8cb6", + "lfs_sha256": "519a092970f55750571c5223b1cfbcb0d36745a678cf41b48d4de6104c2a34e7", + "lfs_size": 135352731, + "xet_hash": "2a1f2087a42350f3ab6f79cda6d7be87ef81f70f3b25f0ed717463812ccdb951" + } + } +} \ No newline at end of file diff --git a/data/real_code2lora/code2lora-evo/.gitattributes b/data/real_code2lora/code2lora-evo/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..bed0738c7eeb449bca98b5d2f33c89a1ee56349a --- /dev/null +++ b/data/real_code2lora/code2lora-evo/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.avro filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.lz4 filter=lfs diff=lfs merge=lfs -text +*.mds filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +# Audio files - uncompressed +*.pcm filter=lfs diff=lfs merge=lfs -text +*.sam filter=lfs diff=lfs merge=lfs -text +*.raw filter=lfs diff=lfs merge=lfs -text +# Audio files - compressed +*.aac filter=lfs diff=lfs merge=lfs -text +*.flac filter=lfs diff=lfs merge=lfs -text +*.mp3 filter=lfs diff=lfs merge=lfs -text +*.ogg filter=lfs diff=lfs merge=lfs -text +*.wav filter=lfs diff=lfs merge=lfs -text +# Image files - uncompressed +*.bmp filter=lfs diff=lfs merge=lfs -text +*.gif filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text +*.tiff filter=lfs diff=lfs merge=lfs -text +# Image files - compressed +*.jpg filter=lfs diff=lfs merge=lfs -text +*.jpeg filter=lfs diff=lfs merge=lfs -text +*.webp filter=lfs diff=lfs merge=lfs -text +# Video files - compressed +*.mp4 filter=lfs diff=lfs merge=lfs -text +*.webm filter=lfs diff=lfs merge=lfs -text diff --git a/data/real_code2lora/code2lora-evo/README.md b/data/real_code2lora/code2lora-evo/README.md new file mode 100644 index 0000000000000000000000000000000000000000..12076d4a9bd34d0eed0b624159820e7c340ac3df --- /dev/null +++ b/data/real_code2lora/code2lora-evo/README.md @@ -0,0 +1,47 @@ +--- +license: mit +pretty_name: Code2LoRA-Evo (evolution track, GRU) +tags: [code, assertion-completion, repository-level] +configs: +- config_name: commits + data_files: + - {split: train, path: commits/train.parquet} + - {split: cr_val, path: commits/cr_val.parquet} + - {split: cr_test, path: commits/cr_test.parquet} +- config_name: qna + data_files: + - {split: train, path: qna/train.parquet} + - {split: cr_val, path: qna/cr_val.parquet} + - {split: cr_test, path: qna/cr_test.parquet} + - {split: ir_val, path: qna/ir_val.parquet} + - {split: ir_test, path: qna/ir_test.parquet} +--- + +# Code2LoRA-Evo — evolution track (GRU) + +Everything the **Code2LoRA-Evo** GRU hypernetwork consumes, post-cap and +self-contained. The GRU walks per-commit `diff_embedding` / +`repo_state_embedding` and is trained with the smart-capped +(`<=8`/commit, `<=4`/file) training QnAs; evaluation uses the paper's +eval-time cap (first `<=8` QnAs per (repo, commit)). + +| config | split | rows | role | +|---|---|---:|---| +| commits | train | 58,617 | per-commit diff + repo-state embeddings | +| commits | cr_val / cr_test | 8,614 / 6,618 | held-out repo commit walks | +| qna | train | 215,129 | smart-capped training loss (`Code2LoRA-Evo`) | +| qna | cr_val | 58,944 | capped eval (`<=8`/commit) | +| qna | cr_test | 44,732 | capped eval | +| qna | ir_val | 38,783 | capped eval | +| qna | ir_test | 42,061 | capped eval | + +Join `commits` and `qna` on `(repo_id, commit_sha)`. + +```python +from datasets import load_dataset +commits = load_dataset("code2lora/code2lora-evo", "commits") +qna = load_dataset("code2lora/code2lora-evo", "qna") +``` + +Companion datasets: `code2lora/code2lora-static`, +`code2lora/code2lora-static-anchor`, `code2lora/repopeftbench-ood`. diff --git a/data/real_code2lora/code2lora-evo/commits/cr_test.parquet b/data/real_code2lora/code2lora-evo/commits/cr_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..1e2ac27253f7cf41412b4a38520e97531302d968 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/commits/cr_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1472bd42bed51428bf1bccbedc4c494db58bc9a6fffa72fc95f95a0613de2169 +size 68411936 diff --git a/data/real_code2lora/code2lora-evo/commits/cr_val.parquet b/data/real_code2lora/code2lora-evo/commits/cr_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..75709b935d623b7edb5ccd83dc0282d1440ac580 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/commits/cr_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73959d38ad7d479a3b6715d96ae22a42ea89c4e9b1830e3f9354ebada98877f +size 88017946 diff --git a/data/real_code2lora/code2lora-evo/commits/train.parquet b/data/real_code2lora/code2lora-evo/commits/train.parquet new file mode 100644 index 0000000000000000000000000000000000000000..ff02daf9b1c12e369523125b664706b7dba70169 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/commits/train.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dfca1e1791fde09c1f310f2be9273b762332f28563d203a2ed7f0136cb3590b +size 612508015 diff --git a/data/real_code2lora/code2lora-evo/qna/cr_test.parquet b/data/real_code2lora/code2lora-evo/qna/cr_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..5d5e537f81519bb5fc611cffc1d2f3e6a643403d --- /dev/null +++ b/data/real_code2lora/code2lora-evo/qna/cr_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc42611e215975824582df0da76984f6a65c3d5e29002a2b205fb5437cde907b +size 16240753 diff --git a/data/real_code2lora/code2lora-evo/qna/cr_val.parquet b/data/real_code2lora/code2lora-evo/qna/cr_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..b979c9c6fc248831d906057a88aa7c123eede5b4 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/qna/cr_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d76ca372ce366ab6f2b51765c9b5cbfbbfa33019b4e05d1dc05c25cacbea04f +size 23488346 diff --git a/data/real_code2lora/code2lora-evo/qna/ir_test.parquet b/data/real_code2lora/code2lora-evo/qna/ir_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..e997fa64278ff967d0c08c22bb9c7a5571c343d5 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/qna/ir_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af20fba7881a55b68efd82302b108615c6a5ae05be8e71d49c3455a7bbb124a4 +size 22805812 diff --git a/data/real_code2lora/code2lora-evo/qna/ir_val.parquet b/data/real_code2lora/code2lora-evo/qna/ir_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..4936c3c5f14b99c30b094b696a7df5f566745ffb --- /dev/null +++ b/data/real_code2lora/code2lora-evo/qna/ir_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b830ddb82490f1c7b6c44104cdcbcd1a8c9ca5f31d3c04af0421d2f0825c6a3 +size 20154479 diff --git a/data/real_code2lora/code2lora-evo/qna/train.parquet b/data/real_code2lora/code2lora-evo/qna/train.parquet new file mode 100644 index 0000000000000000000000000000000000000000..647f3e27841055c9538eec4495520d63e30f8cb6 --- /dev/null +++ b/data/real_code2lora/code2lora-evo/qna/train.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519a092970f55750571c5223b1cfbcb0d36745a678cf41b48d4de6104c2a34e7 +size 135352731 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/.gitignore b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f59ec20aabf5842d237244ece8c81ab184faeac1 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/.gitignore @@ -0,0 +1 @@ +* \ No newline at end of file diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/CACHEDIR.TAG b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/CACHEDIR.TAG new file mode 100644 index 0000000000000000000000000000000000000000..2b927574f362cc41ca52cb6e863dbf47e664febb --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/CACHEDIR.TAG @@ -0,0 +1,4 @@ +Signature: 8a477f597d28d172789f06886806bc55 +# This file is a cache directory tag created by huggingface_hub. +# For information about cache directory tags, see: +# https://bford.info/cachedir/ diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/.gitattributes.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/.gitattributes.metadata new file mode 100644 index 0000000000000000000000000000000000000000..80f1f24018a03bfd448adac696c82f8bf6cd9a80 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/.gitattributes.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +bed0738c7eeb449bca98b5d2f33c89a1ee56349a +1784887199.592155 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/README.md.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..017a74f0651e5454d5d33e792fd976eba70f025f --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/README.md.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +1ee8621fd5030865aab5bef7ac72820d1778810c +1784887199.592134 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/cr_test.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/cr_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..bc817cb166aef09ba9a5df196b278bf834bfded8 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/cr_test.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +2f9f2dfd78618cbb7e39c73deaed6ff9508fccd2491c8aeb4f172797d26b41aa +1784887229.378752 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/cr_val.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/cr_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..df43d3659ed37e0f9e5cca62c32af9500ec691ee --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/cr_val.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +281812bd8d81620a83fa8bac002dbbda6c71ebbfd6a47c1df5c623be41992591 +1784887234.453962 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/ir_test.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/ir_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..3d44058bb28d511634dadbce1e7419a0939a2db8 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/ir_test.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +e0cffc06d2c2f5d42ad42f2ce1b6b32ec54dbde46691cc78bc1e2bd4bb5d02e2 +1784887216.458067 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/ir_val.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/ir_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..72261b6b3cf08bf6b316dbe89115b520a3281ef2 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/ir_val.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +1efa4e7298807fe75ecd81a099908a42e3378eed80cd568659c816f96ab19fa1 +1784887206.041879 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/train.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/train.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..9cef589330a60dcb4dd0b3e55a0ea3bbd47d5f33 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/commits/train.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +e9af541dd34eaf8ec4287b06dfc1b3a5b29f90f1ce7499a51855695786d6a3d2 +1784887202.258442 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/cr_test.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/cr_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..8708f694f3fce8238ad0b9c31c08d543718aff45 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/cr_test.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +fc42611e215975824582df0da76984f6a65c3d5e29002a2b205fb5437cde907b +1784887213.327064 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/cr_val.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/cr_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..131d2d99da2c8b57fdb116ebca605002d491bd6e --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/cr_val.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +3d76ca372ce366ab6f2b51765c9b5cbfbbfa33019b4e05d1dc05c25cacbea04f +1784887225.967221 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/ir_test.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/ir_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..e937f88d53278a47604ea856f610c675eff2597b --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/ir_test.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +af20fba7881a55b68efd82302b108615c6a5ae05be8e71d49c3455a7bbb124a4 +1784887241.1003609 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/ir_val.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/ir_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..712ba2fc7823f33261e0a881f22e09b5950adfa2 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/ir_val.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +6b830ddb82490f1c7b6c44104cdcbcd1a8c9ca5f31d3c04af0421d2f0825c6a3 +1784887232.856902 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/train.parquet.metadata b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/train.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..1b340ac63d38ba28c4b266e61864dc9959253c5c --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/download/qna/train.parquet.metadata @@ -0,0 +1,3 @@ +65b7c77eed9398fc656052d058e9af7c2d432177 +b2fbe5bcd7e916c8d750b654a5b0b7286578f938ed65985eca68cd2936fb5dd1 +1784887223.748132 diff --git a/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/trees/65b7c77eed9398fc656052d058e9af7c2d432177.json b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/trees/65b7c77eed9398fc656052d058e9af7c2d432177.json new file mode 100644 index 0000000000000000000000000000000000000000..ecb23c3b3dfd4b0eff8053b2d84be4a418c98414 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.cache/huggingface/trees/65b7c77eed9398fc656052d058e9af7c2d432177.json @@ -0,0 +1,83 @@ +{ + "format_version": 1, + "files": { + ".gitattributes": { + "size": 2504, + "blob_id": "bed0738c7eeb449bca98b5d2f33c89a1ee56349a" + }, + "README.md": { + "size": 1798, + "blob_id": "1ee8621fd5030865aab5bef7ac72820d1778810c" + }, + "commits/cr_test.parquet": { + "size": 20979060, + "blob_id": "f1a4c3af961e9f98348e4d7ca9ee7fb9ecc07bbc", + "lfs_sha256": "2f9f2dfd78618cbb7e39c73deaed6ff9508fccd2491c8aeb4f172797d26b41aa", + "lfs_size": 20979060, + "xet_hash": "dccd2b6b33cb58024aba877ce8638a79576dbe444b902e054c45d0cc0f873f3a" + }, + "commits/cr_val.parquet": { + "size": 26834450, + "blob_id": "240e8431f81a6332c9b954f4254129e6bef363e4", + "lfs_sha256": "281812bd8d81620a83fa8bac002dbbda6c71ebbfd6a47c1df5c623be41992591", + "lfs_size": 26834450, + "xet_hash": "bfcfcb58af8285525bc2e48a53fe34c40e8d0bb1ba0949e9f6bc8d3f1889211e" + }, + "commits/ir_test.parquet": { + "size": 18069075, + "blob_id": "869388baf5ac4d1634bf743c988829540ba0318f", + "lfs_sha256": "e0cffc06d2c2f5d42ad42f2ce1b6b32ec54dbde46691cc78bc1e2bd4bb5d02e2", + "lfs_size": 18069075, + "xet_hash": "182e622aa94cc1f257d5e8d43b30f54e4b2497dd66dfdd3d54884d42fc27f02a" + }, + "commits/ir_val.parquet": { + "size": 16741758, + "blob_id": "4a0def30c7d746a5eead7de1a977131825ccfc49", + "lfs_sha256": "1efa4e7298807fe75ecd81a099908a42e3378eed80cd568659c816f96ab19fa1", + "lfs_size": 16741758, + "xet_hash": "ba00255aaa6c3f1bd3e297fd8917868a79591eb66bbc2051d79626d3628df556" + }, + "commits/train.parquet": { + "size": 1608634, + "blob_id": "ef5092d91d972ceafe29e6591c2cb145255cdfa9", + "lfs_sha256": "e9af541dd34eaf8ec4287b06dfc1b3a5b29f90f1ce7499a51855695786d6a3d2", + "lfs_size": 1608634, + "xet_hash": "45120132a92dfd70678b173eb110756e934fc6567c1347e04d3272aa148b5c1c" + }, + "qna/cr_test.parquet": { + "size": 16240753, + "blob_id": "5d5e537f81519bb5fc611cffc1d2f3e6a643403d", + "lfs_sha256": "fc42611e215975824582df0da76984f6a65c3d5e29002a2b205fb5437cde907b", + "lfs_size": 16240753, + "xet_hash": "8ee16b74836d3602cf10e960cba16f083e25443e7803da5f411c9af49b3b0b12" + }, + "qna/cr_val.parquet": { + "size": 23488346, + "blob_id": "b979c9c6fc248831d906057a88aa7c123eede5b4", + "lfs_sha256": "3d76ca372ce366ab6f2b51765c9b5cbfbbfa33019b4e05d1dc05c25cacbea04f", + "lfs_size": 23488346, + "xet_hash": "a7764c559c4dda09f842dd904c11d4c7ae340c3b3d941e15fb5e6706cacec1be" + }, + "qna/ir_test.parquet": { + "size": 22805812, + "blob_id": "e997fa64278ff967d0c08c22bb9c7a5571c343d5", + "lfs_sha256": "af20fba7881a55b68efd82302b108615c6a5ae05be8e71d49c3455a7bbb124a4", + "lfs_size": 22805812, + "xet_hash": "9c268ba844d32ab694baf09c446c689289b9e873e4de8f9b9d3cae5470380450" + }, + "qna/ir_val.parquet": { + "size": 20154479, + "blob_id": "4936c3c5f14b99c30b094b696a7df5f566745ffb", + "lfs_sha256": "6b830ddb82490f1c7b6c44104cdcbcd1a8c9ca5f31d3c04af0421d2f0825c6a3", + "lfs_size": 20154479, + "xet_hash": "d51d246ad2ee31868d3a7d16890466349427120f47ef7fc278181d8e1e3d879d" + }, + "qna/train.parquet": { + "size": 7436646, + "blob_id": "b2fcda6096ba240d7aa7bd6c1d8ab8ef1ef7eb2c", + "lfs_sha256": "b2fbe5bcd7e916c8d750b654a5b0b7286578f938ed65985eca68cd2936fb5dd1", + "lfs_size": 7436646, + "xet_hash": "1a44ec7585045f24c0fe8a3eb42d7068e552d0bc74fc5c94af75cb66c74a1cdf" + } + } +} \ No newline at end of file diff --git a/data/real_code2lora/code2lora-static-anchor/.gitattributes b/data/real_code2lora/code2lora-static-anchor/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..bed0738c7eeb449bca98b5d2f33c89a1ee56349a --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.avro filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.lz4 filter=lfs diff=lfs merge=lfs -text +*.mds filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +# Audio files - uncompressed +*.pcm filter=lfs diff=lfs merge=lfs -text +*.sam filter=lfs diff=lfs merge=lfs -text +*.raw filter=lfs diff=lfs merge=lfs -text +# Audio files - compressed +*.aac filter=lfs diff=lfs merge=lfs -text +*.flac filter=lfs diff=lfs merge=lfs -text +*.mp3 filter=lfs diff=lfs merge=lfs -text +*.ogg filter=lfs diff=lfs merge=lfs -text +*.wav filter=lfs diff=lfs merge=lfs -text +# Image files - uncompressed +*.bmp filter=lfs diff=lfs merge=lfs -text +*.gif filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text +*.tiff filter=lfs diff=lfs merge=lfs -text +# Image files - compressed +*.jpg filter=lfs diff=lfs merge=lfs -text +*.jpeg filter=lfs diff=lfs merge=lfs -text +*.webp filter=lfs diff=lfs merge=lfs -text +# Video files - compressed +*.mp4 filter=lfs diff=lfs merge=lfs -text +*.webm filter=lfs diff=lfs merge=lfs -text diff --git a/data/real_code2lora/code2lora-static-anchor/README.md b/data/real_code2lora/code2lora-static-anchor/README.md new file mode 100644 index 0000000000000000000000000000000000000000..1ee8621fd5030865aab5bef7ac72820d1778810c --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/README.md @@ -0,0 +1,45 @@ +--- +license: mit +pretty_name: Code2LoRA-Static anchor (evolution track) +tags: [code, assertion-completion, repository-level] +configs: +- config_name: commits + data_files: + - {split: train, path: commits/train.parquet} + - {split: ir_val, path: commits/ir_val.parquet} + - {split: ir_test, path: commits/ir_test.parquet} + - {split: cr_val, path: commits/cr_val.parquet} + - {split: cr_test, path: commits/cr_test.parquet} +- config_name: qna + data_files: + - {split: train, path: qna/train.parquet} + - {split: cr_val, path: qna/cr_val.parquet} + - {split: cr_test, path: qna/cr_test.parquet} + - {split: ir_val, path: qna/ir_val.parquet} + - {split: ir_test, path: qna/ir_test.parquet} +--- + +# Code2LoRA-Static (anchor) — evolution track + +The direct-projection **Code2LoRA-Static** variant reported in the paper's +evolution-track / per-commit results: one anchor snapshot per repository +with a 2048-d `repo_state_embedding`, no GRU rollout. It shares the +evolution track's capped eval suites with `code2lora/code2lora-evo`. + +| config | split | rows | role | +|---|---|---:|---| +| commits | train | 400 | anchor commit repo-state embeddings | +| commits | ir_val / ir_test | 5,710 / 6,179 | per-commit repo-state (eval) | +| commits | cr_val / cr_test | 8,614 / 6,618 | per-commit repo-state (eval) | +| qna | train | 44,149 | anchor training QnAs (`Code2LoRA-Static`) | +| qna | cr_val / cr_test | 58,944 / 44,732 | capped eval (`<=8`/commit) | +| qna | ir_val / ir_test | 38,783 / 42,061 | capped eval | + +```python +from datasets import load_dataset +commits = load_dataset("code2lora/code2lora-static-anchor", "commits") +qna = load_dataset("code2lora/code2lora-static-anchor", "qna") +``` + +Companion datasets: `code2lora/code2lora-static`, +`code2lora/code2lora-evo`, `code2lora/repopeftbench-ood`. diff --git a/data/real_code2lora/code2lora-static-anchor/commits/cr_test.parquet b/data/real_code2lora/code2lora-static-anchor/commits/cr_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..f1a4c3af961e9f98348e4d7ca9ee7fb9ecc07bbc --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/commits/cr_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9f2dfd78618cbb7e39c73deaed6ff9508fccd2491c8aeb4f172797d26b41aa +size 20979060 diff --git a/data/real_code2lora/code2lora-static-anchor/commits/cr_val.parquet b/data/real_code2lora/code2lora-static-anchor/commits/cr_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..240e8431f81a6332c9b954f4254129e6bef363e4 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/commits/cr_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281812bd8d81620a83fa8bac002dbbda6c71ebbfd6a47c1df5c623be41992591 +size 26834450 diff --git a/data/real_code2lora/code2lora-static-anchor/commits/ir_test.parquet b/data/real_code2lora/code2lora-static-anchor/commits/ir_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..869388baf5ac4d1634bf743c988829540ba0318f --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/commits/ir_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cffc06d2c2f5d42ad42f2ce1b6b32ec54dbde46691cc78bc1e2bd4bb5d02e2 +size 18069075 diff --git a/data/real_code2lora/code2lora-static-anchor/commits/ir_val.parquet b/data/real_code2lora/code2lora-static-anchor/commits/ir_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..4a0def30c7d746a5eead7de1a977131825ccfc49 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/commits/ir_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1efa4e7298807fe75ecd81a099908a42e3378eed80cd568659c816f96ab19fa1 +size 16741758 diff --git a/data/real_code2lora/code2lora-static-anchor/commits/train.parquet b/data/real_code2lora/code2lora-static-anchor/commits/train.parquet new file mode 100644 index 0000000000000000000000000000000000000000..ef5092d91d972ceafe29e6591c2cb145255cdfa9 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/commits/train.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9af541dd34eaf8ec4287b06dfc1b3a5b29f90f1ce7499a51855695786d6a3d2 +size 1608634 diff --git a/data/real_code2lora/code2lora-static-anchor/qna/cr_test.parquet b/data/real_code2lora/code2lora-static-anchor/qna/cr_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..5d5e537f81519bb5fc611cffc1d2f3e6a643403d --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/qna/cr_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc42611e215975824582df0da76984f6a65c3d5e29002a2b205fb5437cde907b +size 16240753 diff --git a/data/real_code2lora/code2lora-static-anchor/qna/cr_val.parquet b/data/real_code2lora/code2lora-static-anchor/qna/cr_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..b979c9c6fc248831d906057a88aa7c123eede5b4 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/qna/cr_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d76ca372ce366ab6f2b51765c9b5cbfbbfa33019b4e05d1dc05c25cacbea04f +size 23488346 diff --git a/data/real_code2lora/code2lora-static-anchor/qna/ir_test.parquet b/data/real_code2lora/code2lora-static-anchor/qna/ir_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..e997fa64278ff967d0c08c22bb9c7a5571c343d5 --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/qna/ir_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af20fba7881a55b68efd82302b108615c6a5ae05be8e71d49c3455a7bbb124a4 +size 22805812 diff --git a/data/real_code2lora/code2lora-static-anchor/qna/ir_val.parquet b/data/real_code2lora/code2lora-static-anchor/qna/ir_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..4936c3c5f14b99c30b094b696a7df5f566745ffb --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/qna/ir_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b830ddb82490f1c7b6c44104cdcbcd1a8c9ca5f31d3c04af0421d2f0825c6a3 +size 20154479 diff --git a/data/real_code2lora/code2lora-static-anchor/qna/train.parquet b/data/real_code2lora/code2lora-static-anchor/qna/train.parquet new file mode 100644 index 0000000000000000000000000000000000000000..b2fcda6096ba240d7aa7bd6c1d8ab8ef1ef7eb2c --- /dev/null +++ b/data/real_code2lora/code2lora-static-anchor/qna/train.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2fbe5bcd7e916c8d750b654a5b0b7286578f938ed65985eca68cd2936fb5dd1 +size 7436646 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/.gitignore b/data/real_code2lora/code2lora-static/.cache/huggingface/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f59ec20aabf5842d237244ece8c81ab184faeac1 --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/.gitignore @@ -0,0 +1 @@ +* \ No newline at end of file diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/CACHEDIR.TAG b/data/real_code2lora/code2lora-static/.cache/huggingface/CACHEDIR.TAG new file mode 100644 index 0000000000000000000000000000000000000000..2b927574f362cc41ca52cb6e863dbf47e664febb --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/CACHEDIR.TAG @@ -0,0 +1,4 @@ +Signature: 8a477f597d28d172789f06886806bc55 +# This file is a cache directory tag created by huggingface_hub. +# For information about cache directory tags, see: +# https://bford.info/cachedir/ diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/.gitattributes.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/.gitattributes.metadata new file mode 100644 index 0000000000000000000000000000000000000000..65c076dd640ca6eb7009d8b315684fa7170765fe --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/.gitattributes.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +bed0738c7eeb449bca98b5d2f33c89a1ee56349a +1784887242.232571 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/README.md.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..908cb6a77ecda8278f751a50fda3359b4ce6e7c1 --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/README.md.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +0a390fc9888809d1fa519fee1965c070112e15dd +1784887242.3327308 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/cr_test.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/cr_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..5b608e6c6996a40fcb90171d517fac9fe501782a --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/cr_test.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +234545feb01789ccfd422d0a02eea7bb43e5587e6be3e90ceca24012b7e665d7 +1784887249.4468322 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/cr_val.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/cr_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..84922d41ea4547b34b007766c5d06d7bdc005b13 --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/cr_val.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +9c05111449e596a1817f61f3b2d728f9ae11031a425bc46e565373897db49272 +1784887248.887584 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/ir_test.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/ir_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..753b7853f99d22a4e5369eb9ae5405a6cc463bbb --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/ir_test.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +7e6261be02c00201b7ed61950cebbeb1297f19f1de92ede70a9e63943747476a +1784887255.800129 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/ir_val.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/ir_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..d5b39e120e9aa7e85f3dfef285ece31c335331e2 --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/ir_val.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +2a1ba08fee4af69d321c8278493a5c3256ea96861c7f35d785e7c90be4657ec6 +1784887257.502165 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/train.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/train.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..4392e25b143e6158f815f1155473e2bd9a46d35b --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/qna/train.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +d5657224e62418a77187285fe55a650ebad1a264bb9edbdc20c7d1e132c9b523 +1784887281.037739 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/cr_test.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/cr_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..2c756d7c0e42bd58cd788c65c78d3b62116d9892 --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/cr_test.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +0d597c8a2462fd407394db40ab9025dc4f4ccc0697a2d4490fdd2a1eab91578f +1784887243.962303 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/cr_val.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/cr_val.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..fafdd8f76d1605f248cbfdb5cf88f6881a77ca7f --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/cr_val.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +8ac1c2477884783356be16f4e2ec5c94c60823df8befb4a2d80813f40c84b794 +1784887244.5128582 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/train.parquet.metadata b/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/train.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..ebb682c115b287a2fd704a66ae66bbcaf7ff5fec --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/download/repos/train.parquet.metadata @@ -0,0 +1,3 @@ +5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4 +ad382500d5bb420e0c8064e7f79d8a26fc12aa8e5b209c95b145a0b4a18dd8ba +1784887245.4021702 diff --git a/data/real_code2lora/code2lora-static/.cache/huggingface/trees/5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4.json b/data/real_code2lora/code2lora-static/.cache/huggingface/trees/5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4.json new file mode 100644 index 0000000000000000000000000000000000000000..6d0414120374de3f284f09a918471b517e3a887e --- /dev/null +++ b/data/real_code2lora/code2lora-static/.cache/huggingface/trees/5ebfd4fabc36b4daf5fb2b056f48ce2d67d3a9d4.json @@ -0,0 +1,69 @@ +{ + "format_version": 1, + "files": { + ".gitattributes": { + "size": 2504, + "blob_id": "bed0738c7eeb449bca98b5d2f33c89a1ee56349a" + }, + "README.md": { + "size": 1728, + "blob_id": "0a390fc9888809d1fa519fee1965c070112e15dd" + }, + "qna/cr_test.parquet": { + "size": 1135371, + "blob_id": "1cf2139711c28afa72a10f0dfe9024c10f58dfac", + "lfs_sha256": "234545feb01789ccfd422d0a02eea7bb43e5587e6be3e90ceca24012b7e665d7", + "lfs_size": 1135371, + "xet_hash": "848670943bd63c697544fcd42e7e10d5bab8fc48a761058b23ce7ca8487ef98a" + }, + "qna/cr_val.parquet": { + "size": 1072168, + "blob_id": "ae3859ef8445b602bc526d1c4c11f1a6a1cc094b", + "lfs_sha256": "9c05111449e596a1817f61f3b2d728f9ae11031a425bc46e565373897db49272", + "lfs_size": 1072168, + "xet_hash": "01cf1f473c0bba25cc2ffa4c5f63ec6a2ef6b52810373b8973b88401519b9f05" + }, + "qna/ir_test.parquet": { + "size": 1937051, + "blob_id": "c3a1fb3e9475b408e9ab95f67d260a5e35cd4805", + "lfs_sha256": "7e6261be02c00201b7ed61950cebbeb1297f19f1de92ede70a9e63943747476a", + "lfs_size": 1937051, + "xet_hash": "3d292a330e156376fa6f9a1382b2125ac76e16d0e81312989bcee5b5d03778ab" + }, + "qna/ir_val.parquet": { + "size": 1863376, + "blob_id": "148a2dd565fe128a70dee6f654e79af362eee324", + "lfs_sha256": "2a1ba08fee4af69d321c8278493a5c3256ea96861c7f35d785e7c90be4657ec6", + "lfs_size": 1863376, + "xet_hash": "3dc1d92b8a274661f77496e7094f40ebe5eecfccaf229eb26ee793a2bedb8b3a" + }, + "qna/train.parquet": { + "size": 8244105, + "blob_id": "a630aba79ffe3b687e1e5cadfe29f654124c0ab5", + "lfs_sha256": "d5657224e62418a77187285fe55a650ebad1a264bb9edbdc20c7d1e132c9b523", + "lfs_size": 8244105, + "xet_hash": "8a96f34aab3c84a21cb6eada4f6e1b1f3788db9f8fdac61908f58eed58e0eae6" + }, + "repos/cr_test.parquet": { + "size": 162337, + "blob_id": "dac2946ca31022023b65638d7c41f8839b3b5246", + "lfs_sha256": "0d597c8a2462fd407394db40ab9025dc4f4ccc0697a2d4490fdd2a1eab91578f", + "lfs_size": 162337, + "xet_hash": "21fa68bac18893e5039a9fcb89f1a149392168b776441d7403207db24aabc6b8" + }, + "repos/cr_val.parquet": { + "size": 158879, + "blob_id": "45081ee65ad256856075403b25cb2bc8bdf332c5", + "lfs_sha256": "8ac1c2477884783356be16f4e2ec5c94c60823df8befb4a2d80813f40c84b794", + "lfs_size": 158879, + "xet_hash": "228234f6b0a9d002b7402924831c6b05f7df4e60ef0a1ba6e517394dffce2802" + }, + "repos/train.parquet": { + "size": 1227071, + "blob_id": "10d626b8250113af3081543662044b77aabe4b61", + "lfs_sha256": "ad382500d5bb420e0c8064e7f79d8a26fc12aa8e5b209c95b145a0b4a18dd8ba", + "lfs_size": 1227071, + "xet_hash": "f0de07ce6c8e272d5a84d650200eb4bd56c9b530c9eb3b27626c843c84c734cd" + } + } +} \ No newline at end of file diff --git a/data/real_code2lora/code2lora-static/.gitattributes b/data/real_code2lora/code2lora-static/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..bed0738c7eeb449bca98b5d2f33c89a1ee56349a --- /dev/null +++ b/data/real_code2lora/code2lora-static/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.avro filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.lz4 filter=lfs diff=lfs merge=lfs -text +*.mds filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +# Audio files - uncompressed +*.pcm filter=lfs diff=lfs merge=lfs -text +*.sam filter=lfs diff=lfs merge=lfs -text +*.raw filter=lfs diff=lfs merge=lfs -text +# Audio files - compressed +*.aac filter=lfs diff=lfs merge=lfs -text +*.flac filter=lfs diff=lfs merge=lfs -text +*.mp3 filter=lfs diff=lfs merge=lfs -text +*.ogg filter=lfs diff=lfs merge=lfs -text +*.wav filter=lfs diff=lfs merge=lfs -text +# Image files - uncompressed +*.bmp filter=lfs diff=lfs merge=lfs -text +*.gif filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text +*.tiff filter=lfs diff=lfs merge=lfs -text +# Image files - compressed +*.jpg filter=lfs diff=lfs merge=lfs -text +*.jpeg filter=lfs diff=lfs merge=lfs -text +*.webp filter=lfs diff=lfs merge=lfs -text +# Video files - compressed +*.mp4 filter=lfs diff=lfs merge=lfs -text +*.webm filter=lfs diff=lfs merge=lfs -text diff --git a/data/real_code2lora/code2lora-static/README.md b/data/real_code2lora/code2lora-static/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0a390fc9888809d1fa519fee1965c070112e15dd --- /dev/null +++ b/data/real_code2lora/code2lora-static/README.md @@ -0,0 +1,49 @@ +--- +license: mit +pretty_name: Code2LoRA-Static (static track, single snapshot) +tags: [code, assertion-completion, repository-level] +configs: +- config_name: qna + data_files: + - {split: train, path: qna/train.parquet} + - {split: cr_val, path: qna/cr_val.parquet} + - {split: cr_test, path: qna/cr_test.parquet} + - {split: ir_val, path: qna/ir_val.parquet} + - {split: ir_test, path: qna/ir_test.parquet} +- config_name: repos + data_files: + - {split: train, path: repos/train.parquet} + - {split: cr_val, path: repos/cr_val.parquet} + - {split: cr_test, path: repos/cr_test.parquet} +--- + +# Code2LoRA-Static — static track (single snapshot) + +The **Static track** of RepoPeftBench exactly as consumed by the paper's +main-results table (`Code2LoRA-Static`, single anchor snapshot per +repository). Contains only the paper-used QnAs (post quality-filter). For +the out-of-distribution slice see `code2lora/repopeftbench-ood`. + +| config | split | rows | +|---|---|---:| +| qna | train | 39,612 | +| qna | cr_val | 6,213 | +| qna | cr_test | 6,414 | +| qna | ir_val | 4,833 | +| qna | ir_test | 5,222 | +| repos | train / cr_val / cr_test | 409 / 51 / 52 | + +* `qna` — one row per assertion pair (`repo_id, prefix, target, + assertion_type, difficulty, test_file, test_function, test_class, + lineno, commit_idx`). +* `repos` — frozen 2048-d Qwen3-Embedding repo-state vector per repo + (`repo_id, embedding`); IR suites reuse the train-repo embeddings. + +```python +from datasets import load_dataset +qna = load_dataset("code2lora/code2lora-static", "qna") +repos = load_dataset("code2lora/code2lora-static", "repos") +``` + +Companion datasets: `code2lora/code2lora-evo`, +`code2lora/code2lora-static-anchor`, `code2lora/repopeftbench-ood`. diff --git a/data/real_code2lora/code2lora-static/qna/cr_test.parquet b/data/real_code2lora/code2lora-static/qna/cr_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..1cf2139711c28afa72a10f0dfe9024c10f58dfac --- /dev/null +++ b/data/real_code2lora/code2lora-static/qna/cr_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234545feb01789ccfd422d0a02eea7bb43e5587e6be3e90ceca24012b7e665d7 +size 1135371 diff --git a/data/real_code2lora/code2lora-static/qna/cr_val.parquet b/data/real_code2lora/code2lora-static/qna/cr_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..ae3859ef8445b602bc526d1c4c11f1a6a1cc094b --- /dev/null +++ b/data/real_code2lora/code2lora-static/qna/cr_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c05111449e596a1817f61f3b2d728f9ae11031a425bc46e565373897db49272 +size 1072168 diff --git a/data/real_code2lora/code2lora-static/qna/ir_test.parquet b/data/real_code2lora/code2lora-static/qna/ir_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..c3a1fb3e9475b408e9ab95f67d260a5e35cd4805 --- /dev/null +++ b/data/real_code2lora/code2lora-static/qna/ir_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e6261be02c00201b7ed61950cebbeb1297f19f1de92ede70a9e63943747476a +size 1937051 diff --git a/data/real_code2lora/code2lora-static/qna/ir_val.parquet b/data/real_code2lora/code2lora-static/qna/ir_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..148a2dd565fe128a70dee6f654e79af362eee324 --- /dev/null +++ b/data/real_code2lora/code2lora-static/qna/ir_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1ba08fee4af69d321c8278493a5c3256ea96861c7f35d785e7c90be4657ec6 +size 1863376 diff --git a/data/real_code2lora/code2lora-static/qna/train.parquet b/data/real_code2lora/code2lora-static/qna/train.parquet new file mode 100644 index 0000000000000000000000000000000000000000..a630aba79ffe3b687e1e5cadfe29f654124c0ab5 --- /dev/null +++ b/data/real_code2lora/code2lora-static/qna/train.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5657224e62418a77187285fe55a650ebad1a264bb9edbdc20c7d1e132c9b523 +size 8244105 diff --git a/data/real_code2lora/code2lora-static/repos/cr_test.parquet b/data/real_code2lora/code2lora-static/repos/cr_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..dac2946ca31022023b65638d7c41f8839b3b5246 --- /dev/null +++ b/data/real_code2lora/code2lora-static/repos/cr_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d597c8a2462fd407394db40ab9025dc4f4ccc0697a2d4490fdd2a1eab91578f +size 162337 diff --git a/data/real_code2lora/code2lora-static/repos/cr_val.parquet b/data/real_code2lora/code2lora-static/repos/cr_val.parquet new file mode 100644 index 0000000000000000000000000000000000000000..45081ee65ad256856075403b25cb2bc8bdf332c5 --- /dev/null +++ b/data/real_code2lora/code2lora-static/repos/cr_val.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac1c2477884783356be16f4e2ec5c94c60823df8befb4a2d80813f40c84b794 +size 158879 diff --git a/data/real_code2lora/code2lora-static/repos/train.parquet b/data/real_code2lora/code2lora-static/repos/train.parquet new file mode 100644 index 0000000000000000000000000000000000000000..10d626b8250113af3081543662044b77aabe4b61 --- /dev/null +++ b/data/real_code2lora/code2lora-static/repos/train.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad382500d5bb420e0c8064e7f79d8a26fc12aa8e5b209c95b145a0b4a18dd8ba +size 1227071 diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/.gitignore b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f59ec20aabf5842d237244ece8c81ab184faeac1 --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/.gitignore @@ -0,0 +1 @@ +* \ No newline at end of file diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/CACHEDIR.TAG b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/CACHEDIR.TAG new file mode 100644 index 0000000000000000000000000000000000000000..2b927574f362cc41ca52cb6e863dbf47e664febb --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/CACHEDIR.TAG @@ -0,0 +1,4 @@ +Signature: 8a477f597d28d172789f06886806bc55 +# This file is a cache directory tag created by huggingface_hub. +# For information about cache directory tags, see: +# https://bford.info/cachedir/ diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/.gitattributes.metadata b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/.gitattributes.metadata new file mode 100644 index 0000000000000000000000000000000000000000..f0df1311407372e7ff220049524c2a276afd94ed --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/.gitattributes.metadata @@ -0,0 +1,3 @@ +3e465354c5cdcdc528e6770b201bc0de30634b2f +bed0738c7eeb449bca98b5d2f33c89a1ee56349a +1784887282.477484 diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/README.md.metadata b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/README.md.metadata new file mode 100644 index 0000000000000000000000000000000000000000..03378078bda9faaf2429ac20d79be22ab66d154b --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/README.md.metadata @@ -0,0 +1,3 @@ +3e465354c5cdcdc528e6770b201bc0de30634b2f +386b5551b45aa00d3c005ae2a7330b6a070b1313 +1784887282.063957 diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/commits/ood_test.parquet.metadata b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/commits/ood_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..25faa91a9def3b5fa2cbd2a2319bda22dc96b5b0 --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/commits/ood_test.parquet.metadata @@ -0,0 +1,3 @@ +3e465354c5cdcdc528e6770b201bc0de30634b2f +c1c528109824941478cb3b1b43c62ba38aadce1fc0d9be6b3f5038638696584b +1784887362.61373 diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/qna_evo/ood_test.parquet.metadata b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/qna_evo/ood_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..79e14f6ee3423443c6e89d0192e0a8a52c9afe79 --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/qna_evo/ood_test.parquet.metadata @@ -0,0 +1,3 @@ +3e465354c5cdcdc528e6770b201bc0de30634b2f +dcc3c15777b957a54e40ab5486d4d5ecab658ab9e663f4d68c50ead8158e4e81 +1784887289.001732 diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/qna_static/ood_test.parquet.metadata b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/qna_static/ood_test.parquet.metadata new file mode 100644 index 0000000000000000000000000000000000000000..fb821e79e3b5e0f7c1efc312bff3122b46ab163a --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/download/qna_static/ood_test.parquet.metadata @@ -0,0 +1,3 @@ +3e465354c5cdcdc528e6770b201bc0de30634b2f +af868abf435b419e847557c587281281aec5fd34e6768fd24108d1edbfb4b248 +1784887285.163815 diff --git a/data/real_code2lora/repopeftbench-ood/.cache/huggingface/trees/3e465354c5cdcdc528e6770b201bc0de30634b2f.json b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/trees/3e465354c5cdcdc528e6770b201bc0de30634b2f.json new file mode 100644 index 0000000000000000000000000000000000000000..cd331b18c91fbb6f2c0c732be2f77173adb5f0ab --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.cache/huggingface/trees/3e465354c5cdcdc528e6770b201bc0de30634b2f.json @@ -0,0 +1,34 @@ +{ + "format_version": 1, + "files": { + ".gitattributes": { + "size": 2504, + "blob_id": "bed0738c7eeb449bca98b5d2f33c89a1ee56349a" + }, + "README.md": { + "size": 1287, + "blob_id": "386b5551b45aa00d3c005ae2a7330b6a070b1313" + }, + "commits/ood_test.parquet": { + "size": 60262226, + "blob_id": "fad0bdb81b19c41fd54eaacb4a26169a6f268572", + "lfs_sha256": "c1c528109824941478cb3b1b43c62ba38aadce1fc0d9be6b3f5038638696584b", + "lfs_size": 60262226, + "xet_hash": "48d97d3bbb9f83b5cb310141747aea65d8cc9b25d40e51034cbe862ff408d6d0" + }, + "qna_evo/ood_test.parquet": { + "size": 3082386, + "blob_id": "c1b6433e80bf533f9eac7c7daf27c85aa04a418b", + "lfs_sha256": "dcc3c15777b957a54e40ab5486d4d5ecab658ab9e663f4d68c50ead8158e4e81", + "lfs_size": 3082386, + "xet_hash": "1c6433ce3bd9f13a1900022543fe64fa5757064e46c58b352319ccdfde5a3dbc" + }, + "qna_static/ood_test.parquet": { + "size": 1009240, + "blob_id": "d6a299ca083e4aa579a36dd195a81ff886224c5b", + "lfs_sha256": "af868abf435b419e847557c587281281aec5fd34e6768fd24108d1edbfb4b248", + "lfs_size": 1009240, + "xet_hash": "fcbde5fcdbaa2986f0872f4f65ec4f7d0abc910f3c1f4dfd603631df9630a236" + } + } +} \ No newline at end of file diff --git a/data/real_code2lora/repopeftbench-ood/.gitattributes b/data/real_code2lora/repopeftbench-ood/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..bed0738c7eeb449bca98b5d2f33c89a1ee56349a --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.avro filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.lz4 filter=lfs diff=lfs merge=lfs -text +*.mds filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +# Audio files - uncompressed +*.pcm filter=lfs diff=lfs merge=lfs -text +*.sam filter=lfs diff=lfs merge=lfs -text +*.raw filter=lfs diff=lfs merge=lfs -text +# Audio files - compressed +*.aac filter=lfs diff=lfs merge=lfs -text +*.flac filter=lfs diff=lfs merge=lfs -text +*.mp3 filter=lfs diff=lfs merge=lfs -text +*.ogg filter=lfs diff=lfs merge=lfs -text +*.wav filter=lfs diff=lfs merge=lfs -text +# Image files - uncompressed +*.bmp filter=lfs diff=lfs merge=lfs -text +*.gif filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text +*.tiff filter=lfs diff=lfs merge=lfs -text +# Image files - compressed +*.jpg filter=lfs diff=lfs merge=lfs -text +*.jpeg filter=lfs diff=lfs merge=lfs -text +*.webp filter=lfs diff=lfs merge=lfs -text +# Video files - compressed +*.mp4 filter=lfs diff=lfs merge=lfs -text +*.webm filter=lfs diff=lfs merge=lfs -text diff --git a/data/real_code2lora/repopeftbench-ood/README.md b/data/real_code2lora/repopeftbench-ood/README.md new file mode 100644 index 0000000000000000000000000000000000000000..386b5551b45aa00d3c005ae2a7330b6a070b1313 --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/README.md @@ -0,0 +1,36 @@ +--- +license: mit +pretty_name: RepoPeftBench OOD holdout (static + evolution) +tags: [code, assertion-completion, repository-level, ood] +configs: +- config_name: commits + data_files: + - {split: ood_test, path: commits/ood_test.parquet} +- config_name: qna_static + data_files: + - {split: ood_test, path: qna_static/ood_test.parquet} +- config_name: qna_evo + data_files: + - {split: ood_test, path: qna_evo/ood_test.parquet} +--- + +# RepoPeftBench — OOD holdout (static + evolution) + +Post-cutoff out-of-distribution repositories, holding both evaluation +views used in the paper's OOD table, post-cap and self-contained. + +| config | split | rows | role | +|---|---|---:|---| +| commits | ood_test | 1,950 | per-commit diff + repo-state embeddings (GRU / anchor) | +| qna_static | ood_test | 9,942 | static-track prompts (prompt-based OOD rows) | +| qna_evo | ood_test | 14,813 | commit-derived capped eval (`<=8`/commit) | + +```python +from datasets import load_dataset +commits = load_dataset("code2lora/repopeftbench-ood", "commits") +qna_static = load_dataset("code2lora/repopeftbench-ood", "qna_static") +qna_evo = load_dataset("code2lora/repopeftbench-ood", "qna_evo") +``` + +Companion datasets: `code2lora/code2lora-static`, +`code2lora/code2lora-evo`, `code2lora/code2lora-static-anchor`. diff --git a/data/real_code2lora/repopeftbench-ood/commits/ood_test.parquet b/data/real_code2lora/repopeftbench-ood/commits/ood_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..fad0bdb81b19c41fd54eaacb4a26169a6f268572 --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/commits/ood_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c528109824941478cb3b1b43c62ba38aadce1fc0d9be6b3f5038638696584b +size 60262226 diff --git a/data/real_code2lora/repopeftbench-ood/qna_evo/ood_test.parquet b/data/real_code2lora/repopeftbench-ood/qna_evo/ood_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..c1b6433e80bf533f9eac7c7daf27c85aa04a418b --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/qna_evo/ood_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc3c15777b957a54e40ab5486d4d5ecab658ab9e663f4d68c50ead8158e4e81 +size 3082386 diff --git a/data/real_code2lora/repopeftbench-ood/qna_static/ood_test.parquet b/data/real_code2lora/repopeftbench-ood/qna_static/ood_test.parquet new file mode 100644 index 0000000000000000000000000000000000000000..d6a299ca083e4aa579a36dd195a81ff886224c5b --- /dev/null +++ b/data/real_code2lora/repopeftbench-ood/qna_static/ood_test.parquet @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af868abf435b419e847557c587281281aec5fd34e6768fd24108d1edbfb4b248 +size 1009240