diff --git a/.gitattributes b/.gitattributes index f7e84b3596d409dd83b98b73e999ff307cc95023..1b03166505dd125bb9ac30d32a6f460b6c806300 100644 --- a/.gitattributes +++ b/.gitattributes @@ -73,3 +73,39 @@ pytorch_model-00037-of-00039.bin filter=lfs diff=lfs merge=lfs -text pytorch_model-00038-of-00039.bin filter=lfs diff=lfs merge=lfs -text finetuned_conversations.pth filter=lfs diff=lfs merge=lfs -text pytorch_model.bin filter=lfs diff=lfs merge=lfs -text +adapter_model.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model_trainer_llama_7b.bin filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00006-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00008-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00018-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00023-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00025-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00009-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00024-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00015-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00021-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00032-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00005-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00007-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00016-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00030-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00014-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00028-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00029-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00010-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00011-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00013-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00019-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00020-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00022-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00026-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00002-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00004-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00012-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00017-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00003-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00027-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00031-of-00033.bin filter=lfs diff=lfs merge=lfs -text +decapoda-research/llama-7b-hf/pytorch_model-00033-of-00033.bin filter=lfs diff=lfs merge=lfs -text diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..88297638cf64b5204c61826f8aa7545b7fb4e836 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5cb2ef8a6558c0ce314bcc11e4a15d0df379222ad7753ae9f75591cc87c945d +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00001-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00001-of-00039.bin deleted file mode 100644 index 437c45b50b816dff8eb1017b79d4bcd793664d5f..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00001-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a6d643b042185fc9a594be1fc68d6cf28e7c4066e77faf35e2e32968ab9640fe -size 396364479 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00002-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00002-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..bde1dbcc4b320e9856265f1fa29fc8fbc16a9dd8 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00002-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba688e4ab77a5a95aebf52e0aa508d31ec1c02b6b5078191379c158526e6c12 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00002-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00002-of-00039.bin deleted file mode 100644 index 8862937e272eb1a6f4b7e9d0514e9ab9d61a77db..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00002-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e0ed40da66089a977c250d7e8a3d7fb6939f369c75986fad0aa0e72cc1c1f610 -size 371215393 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00003-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00003-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..92c074bc000617b9ae0224a2a606038e5fc81a92 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00003-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ce0f7e5e8c374e697ded9576dfc5023f83e3c4c8a65dce63c009401672d2ca +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00003-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00003-of-00039.bin deleted file mode 100644 index c224dff3795ec872adca86d478d1203226f5d8af..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00003-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8b0989d7cb39aca231afcff32cbcab29327cc9c45b3d8ec006391571ff2c9949 -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00004-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00004-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..19a39a48d30dc7a88c1236796a25b8dbd89f03da --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00004-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfe1d1093cbbb04d36b4fd09978e87077e41b4492b8cbba6bfff57c8dbd86dd +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00004-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00004-of-00039.bin deleted file mode 100644 index 5a6d4464e89ff00ccd333a41d758a5dc3ccb93d3..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00004-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:023abb6adea627df974e693778f82bcf8da839678a496f8c3a2e308bba2b5eaa -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00005-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00005-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..851af5aee62a674abd99473e29348d8be0d5657e --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00005-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8014666b4da29ee637d96030f5e7612d2f2dff79a4df8ad4aafcb0125357d3 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00005-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00005-of-00039.bin deleted file mode 100644 index e17093b2a9566cf5565c8d6939af8f15b7c37252..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00005-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:97490b8826e471d3f9286fbfe0551ab8c39f7c14729792d1f999221ebd495294 -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00006-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00006-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..4a3ba3e2fb851c87c7021ae2af19f47b121e49ef --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00006-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d708f41d25ad5461d979337713757fabfe76c375b205b536bfe14d48556d5e0 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00006-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00006-of-00039.bin deleted file mode 100644 index b4799ea59c435acd9d7c8cba9ca099a9bb6cdab8..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00006-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc0ac91d6f83699efd72e527a7e48e6f7f997e2807ff5b537a13783864d15bf5 -size 314575888 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00007-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00007-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..828dc15089e8acc7450904857d62894b371744a6 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00007-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6b78baebf20d60da825c3654c202008acfc3056c84cb6dadd91b155d278e38 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00007-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00007-of-00039.bin deleted file mode 100644 index 1c63867c2fd02e8b0187302875feed0db0628bc4..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00007-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ceaf76a78fefbd8937c2342e09d3ad37a1f0f7257f9b7698e2f9d0579b180e2f -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00008-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00008-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..67e0f97d5b46720372d909e56d6c32aa12007efd --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00008-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6080c736b3136935f0d3fb9fc65b41008c65b6b7d5238e1b9c4780043f31b955 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00008-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00008-of-00039.bin deleted file mode 100644 index 59d87e07a78fe2c6fb05ee6db8ef878c8d99cd09..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00008-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b822e54cca11c7dffbb5c5bc3e864afeff8c26a19d75da35802127e58efc2b74 -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00009-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00009-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa312287d3fc0c99cbf9db76fa86544cb9915d95 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00009-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90047b0adfef1abc939032be63cbe62300d3ee18b39251c2f36d362d6735b64e +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00009-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00009-of-00039.bin deleted file mode 100644 index 362e20f33ff0cda4bc2074fc40ad13f15aa7ab20..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00009-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1158dca80b45679d989baee30469c1eb5a728c1d27efbafd41d5791afd929ecd -size 371215393 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00010-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00010-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a9f7b1911702d4b578f4aa98966c3aedee0403e --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00010-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec40a890dc20ddf9b49a6e1b18e26a304adbe701374a92f0295a7975139fa4b3 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00010-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00010-of-00039.bin deleted file mode 100644 index a723b033445336c700a8d76ff35aa78aa97d4280..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00010-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ad808f8aa6157a7f218466b5fb6a712ec0869aeba8f1913d302205ef84c41517 -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00011-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00011-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..5167f264fd71adc8c02b2d770a9cb5e54b855159 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00011-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d551e0c80f82a61a1cbf74389651359c3fb35ce50c4568256ebc8dcf7c1fcd3 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00011-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00011-of-00039.bin deleted file mode 100644 index 1bc0dd2f3d1e9eca83a3a788bfadf7322396de77..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00011-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1730e511925d15b9dc43a5d224e46142fa48430182cfea3b0e055353c26d9acd -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00012-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00012-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..a3b21e1bcc631679dd7884f98b94aa336d3e9f67 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00012-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:869ac6cceca6c9f26d13ac05549b5e15d79acb90a0593475260171c29f3b9c73 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00012-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00012-of-00039.bin deleted file mode 100644 index 485f2cceb90503ac996fe4af400b4dd56eedfbd5..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00012-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ed49d27e7392e8c695db256c9edacbe5fec2e30f613e91f9f9a34881f9f14e2e -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00013-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00013-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..947244d5241f6d6d3e36215c78a9eb63e7acb213 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00013-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a18845375f10dc0085adc387f21e6ddc372338e767d1879c6369c11b27cb9b97 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00013-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00013-of-00039.bin deleted file mode 100644 index aa1ae1a5bec719e7f02ba21b420afa325ebdfcea..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00013-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0c634fe5358313e99f110bcdc2d2eca4193456f393849157bdda034f343e44bd -size 314575888 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00014-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00014-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..d9cc7ad6ccc2619a334ed59433be38dbda48c041 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00014-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e5dbe9332ea27857a2f9b8ef80e34567ff5d6f5855daffd73292080aedb401 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00014-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00014-of-00039.bin deleted file mode 100644 index a068c6b4ba6d21e9f5e2e509b9499d8d54c4e2fa..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00014-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fa18c41f5d4c3dd3102601ff438b2032adfcb970f7c73589bdd80edf3a8d15ba -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00015-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00015-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d787959204f4520c11f5d08f2c61b3003f92143 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00015-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c259f397f43ccb73919b40810c4b33638bc655301a80805374800c124216ec80 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00015-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00015-of-00039.bin deleted file mode 100644 index de036ebba1a023efa5152de9f16e56cc20877ea9..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00015-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1ea3fa408d8d15e7f63866caf8d726895f5b572576caa8fb7fbbb513724355c3 -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00016-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00016-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..c03cf768b327cb7ded544f02a7edd8d92b9da0f4 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00016-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada30914f430170e601b4638ade39cbebb2cab280763ad5310492a35fed05082 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00016-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00016-of-00039.bin deleted file mode 100644 index 487634777ec0042b32958680469578a31ff337e9..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00016-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:411890749b8ce0783b8197eb7e4968f8a49ed4619a93a7453641c1a7106ddf59 -size 371215393 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00017-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00017-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..750050ac1fc50c5743c90ea5b69d77fc6b07654d --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00017-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f30a61cf2d7bef7ea0b927e05cd0f43d0aee6e00de73a9f7ba56f99deb4e3905 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00017-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00017-of-00039.bin deleted file mode 100644 index 03b107de61448745889119f62cb26cf457ac82dc..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00017-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ab871faecd52b6f8b7cbafc577e2a059db5ec1fbd8ab8b5ef5da6a2ceffd5a5e -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00018-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00018-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..d88c3f76d462c5ab60b863b03bfe24781bad56b2 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00018-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e13fe2d35345fe65a1f7d4af98cf9a40f758f2403bd68a7e8ca4dbf50598014 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00018-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00018-of-00039.bin deleted file mode 100644 index a66444f8cbbf2952ca147fcdf607d19eeab26829..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00018-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:19b7cd10832736214705d9eb2675b9b1667cd8d3c5fe107f1df85c649fbfa16a -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00019-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00019-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ade0efe25cc62eb6f1b8ddf35a886c6d57a68db --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00019-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c993cd7044316208e3b8d8564d929e95bb57328dab63848fbb729b10049861eb +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00019-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00019-of-00039.bin deleted file mode 100644 index 8a6f0070144ae9bfeb29cb3f960699b40463200d..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00019-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:83c4729335ed1226347a32477333cec4a85e0be6ec535ebf019e3c59c34b8e88 -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00020-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00020-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..09a0a0b76d92c155c6b46b0dd9bbc41dc6ba7582 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00020-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb454682956e64a8c7c035764a6110dbb76fd7c61285160b42b06e7f0b5db0f2 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00020-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00020-of-00039.bin deleted file mode 100644 index 1fbf87762cf9e1a535a33e2d97f9bd3d045a1813..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00020-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bfae9635bb7c9ade7ad218f886ed7f7007fc923d219dd40eedd6db36e43aaba0 -size 314575888 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00021-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00021-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..7fbed380ba6b895fc5983a938a8bcd49b468375b --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00021-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b35993de04e54aad4a034da33ae2860220482c0be5f5c2b9555c13f969f6531 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00021-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00021-of-00039.bin deleted file mode 100644 index c970299b35cad7cc79c74f982acf02ea0c73724d..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00021-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3deb7dbc21695274e1641c82c9134666ed9630044b48eb18453701118989e57b -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00022-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00022-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..5bd0b716fac017b691a53f440c827828a0f1647f --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00022-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3cb8f788c63a46e026ae54fca16aeb57d0af45e22bed01124dee12c266cf00d +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00022-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00022-of-00039.bin deleted file mode 100644 index 5c33520041932339d1df696c5c70d728a8292c7e..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00022-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:202d7ce7a775b273cc9badd35a075a68ac85abb0c207d71627f8c9ac80593e83 -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00023-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00023-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..939e893b5628cfda5ca277dc3eebb88a404143d3 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00023-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd034aad548c5423a8b4e07a4c44d8c2be1c350f9e8681cfdf0e63328fabadf9 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00023-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00023-of-00039.bin deleted file mode 100644 index 4a1d090b9fcd4f57b5724b837195bf0e3a925748..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00023-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ce200b7acec4d97dc935cc5c3d3bd675f1106293fe3a431a4db011a55e79707 -size 371215393 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00024-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00024-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..38e442514f57bf9ae9e25248e03a7b8145ad5089 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00024-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d306be39a567f349b9e7bdc8b2543158607ca8834d8c71d32e1b648367ca94 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00024-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00024-of-00039.bin deleted file mode 100644 index 7138d6df86d797712b4de47a42ea751a7ecabbe9..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00024-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:32fd7a47923af58e16eeac3cd30522e2d996b0b8b5e1a679218740b4ca7c560c -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00025-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00025-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..81770833674a192a4ae25624177cdf6d0ccc8bd9 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00025-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d794d97063fb3c24ce913efa473b393dc6330aa67b00a47c4a91428de03896bc +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00025-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00025-of-00039.bin deleted file mode 100644 index 73f2594ff760043860cabcdac02fd6129c2caa5b..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00025-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3231fe826a54070bc50bc079411ce3e053f2754cfc1df99d81636a1e65f2e96d -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00026-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00026-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..160951a4a6aa9847d511bf60ca589cd7e1e90768 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00026-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aef4f0698b0670d6e9c83ca103c3c8dff70e2f237065e2c7293f496933ead0e +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00026-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00026-of-00039.bin deleted file mode 100644 index 1b20f9d505b96b02eff422e616b551188ec41858..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00026-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f5f327d3225017f9a76a709ea5f3cfd8a7ac31201fa982a91e656abe79c681a9 -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00027-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00027-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..4dfcc8347c76ba0295901161763e3bd6d6b335ce --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00027-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c06dbeda998897337596e8d98d53be174083a09a049640bf4f31eef37f56ea0 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00027-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00027-of-00039.bin deleted file mode 100644 index 45bb7ae8aa28e840d4a808638aaa4612c684dc95..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00027-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:13e36fad51e0ed450a26f6a0df0e5a54da36cc9b11880fa1e6cb78f547523c2f -size 314575888 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00028-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00028-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..93b6e02457348132d7547862d5840126534b0e7c --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00028-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b38acac958aadb83ae22e7317a82ff64caccde6f0c02539bd499e8777218af +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00028-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00028-of-00039.bin deleted file mode 100644 index 219566d6bd67f007952499a202d95b8a5c277366..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00028-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:70bdade42999a45556acbc59f84e243c914727ff3a0df21def1aec910c8a1a63 -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00029-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00029-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a0537c6cb1a804c57ea6d4d98babfabf419d3f3 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00029-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798176e2a686e6ae5e9532d1943baaee618190f81f52311610c91603c6408fa7 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00029-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00029-of-00039.bin deleted file mode 100644 index 98d0ca1fe7d074489de0b58abf9442a21b838ef9..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00029-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:309a55d4438eeb420fe55d0d5f2f839b2a57a70b5319b9c52944e6820d152907 -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00030-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00030-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..3af4a95d286627ddce5c36a5dfb33ee230e0f2b6 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00030-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce7a9ef1002e65ff614d8237d6a643b4b6b96ef68b260532f219c692884f9b70 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00030-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00030-of-00039.bin deleted file mode 100644 index e66c6cd2f02696fc0ab29edcbf53f7be892ae307..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00030-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2140a18cc1022babc308c1dfafe9a3703536f4aa941e6b0b4fab5d0f7ef396c9 -size 371215393 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00031-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00031-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a94f67a5ce043d70a76edf80aa5673079191f43 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00031-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e746351f91d9d482c534620a441a7a66474fa9da57104b65f821fc513bad663 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00031-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00031-of-00039.bin deleted file mode 100644 index eec1c0d869ab1e244b2c0e2a1eb53fa5c9df2f69..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00031-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c37701696a1dd25937001b8c155581f56c0448db200a20bd41bcb769702cf6bb -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00032-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00032-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..700e4e3c5f0da416672d42622c559e2584b05601 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00032-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a865bd2b40a83e2110bb0a7de97dd08d7852b3858538ec5d65f64084667e44 +size 404770755 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00032-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00032-of-00039.bin deleted file mode 100644 index 89b1343b02d9df1bcb7affce6436f0ed9f340dbf..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00032-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1da7fdd75386dcb49549fe47512cfe121bc1e1b35288009d02ab86563810d48d -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00033-of-00033.bin b/decapoda-research/llama-7b-hf/pytorch_model-00033-of-00033.bin new file mode 100644 index 0000000000000000000000000000000000000000..71cea93b218bde61c9022ca330e7709727c43950 --- /dev/null +++ b/decapoda-research/llama-7b-hf/pytorch_model-00033-of-00033.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f289012ffe06b1aee0bebdfaea70a394c60444370d9b31c9ab0a7ccd7a4ee415 +size 524297676 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00033-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00033-of-00039.bin deleted file mode 100644 index 33521a7299d66a2cb3628b984d61160dedddef08..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00033-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d764c98487c12227781ddc2d03abc1f958cdf9c524b7e453f83d15d31b26410 -size 371215986 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00034-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00034-of-00039.bin deleted file mode 100644 index 6e7e8094bef10ccb54cdfcff675c1dfbf533fe47..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00034-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a507e79cc1a1f3051b30811b370c386869c2daf283ff06dbcba6413ee2882722 -size 314575888 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00035-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00035-of-00039.bin deleted file mode 100644 index c20cb6287f7363b3f36f5f37fd2ec892023fd750..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00035-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:334c947fae96c0a2276fb2d31793a65587df1d5f61b3630a3dfe7a775a7cfd1d -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00036-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00036-of-00039.bin deleted file mode 100644 index ece1b14e57c330de2a196180603cba55dcef6acc..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00036-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5fb6b4edf40d19fc271b621de8e29d3411365f963e44f9cc8ad61f00a12b76c5 -size 314592882 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00037-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00037-of-00039.bin deleted file mode 100644 index cea726174ac3142de9c315fcd6a912e82a6a5d59..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00037-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:52e53bf5779a24d9f7c9a73cf0e57f5b1bcb0a52c200ddb51f7e55bc76736107 -size 371215393 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00038-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00038-of-00039.bin deleted file mode 100644 index 62fc982325a86687f169311e9a5a10dbc0612a2d..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00038-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6762c675eb30868665ce8ada7a2bbbd117e02f44d47ba3c8dcf91f5623e5ce67 -size 304114977 diff --git a/decapoda-research/llama-7b-hf/pytorch_model-00039-of-00039.bin b/decapoda-research/llama-7b-hf/pytorch_model-00039-of-00039.bin deleted file mode 100644 index 560e955010019c26435b05bfc3412c70b4888b2e..0000000000000000000000000000000000000000 --- a/decapoda-research/llama-7b-hf/pytorch_model-00039-of-00039.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3350fb71c2bc1e88d77d9685716fd2759e879137814a4120d98265a43f405919 -size 262144938 diff --git a/notebooks/HuggingFace-Inference.ipynb b/notebooks/HuggingFace-Inference.ipynb new file mode 100644 index 0000000000000000000000000000000000000000..b974278ad901491b7b4cdc2445c25f4f13a8a0d1 --- /dev/null +++ b/notebooks/HuggingFace-Inference.ipynb @@ -0,0 +1,832 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 5, + "id": "9837afb7", + "metadata": {}, + "outputs": [], + "source": [ + "def generate_prompt(instruction: str, input_ctxt: str = None) -> str:\n", + " if input_ctxt:\n", + " return f\"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", + "\n", + "### Instruction:\n", + "{instruction}\n", + "\n", + "### Input:\n", + "{input_ctxt}\n", + "\n", + "### Response:\"\"\"\n", + " else:\n", + " return f\"\"\"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n", + "\n", + "### Instruction:\n", + "{instruction}\n", + "\n", + "### Response:\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "1cb5103c", + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "bff8fb0a005e4635a07ecf6fe0fdba88", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "Loading checkpoint shards: 0%| | 0/33 [00:00╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/modeling_utils.py:45 │\n", + "│ 9 in load_state_dict │\n", + "│ │\n", + "│ 456 │ │ │ ) │\n", + "│ 457 │ │ return safe_load_file(checkpoint_file) │\n", + "│ 458 │ try: │\n", + "│ ❱ 459 │ │ return torch.load(checkpoint_file, map_location=\"cpu\") │\n", + "│ 460 │ except Exception as e: │\n", + "│ 461 │ │ try: │\n", + "│ 462 │ │ │ with open(checkpoint_file) as f: │\n", + "│ │\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/torch/serialization.py:791 in │\n", + "│ load │\n", + "│ │\n", + "│ 788 │ if 'encoding' not in pickle_load_args.keys(): │\n", + "│ 789 │ │ pickle_load_args['encoding'] = 'utf-8' │\n", + "│ 790 │ │\n", + "│ ❱ 791 │ with _open_file_like(f, 'rb') as opened_file: │\n", + "│ 792 │ │ if _is_zipfile(opened_file): │\n", + "│ 793 │ │ │ # The zipfile reader is going to advance the current file position. │\n", + "│ 794 │ │ │ # If we want to actually tail call to torch.jit.load, we need to │\n", + "│ │\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/torch/serialization.py:271 in │\n", + "│ _open_file_like │\n", + "│ │\n", + "│ 268 │\n", + "│ 269 def _open_file_like(name_or_buffer, mode): │\n", + "│ 270 │ if _is_path(name_or_buffer): │\n", + "│ ❱ 271 │ │ return _open_file(name_or_buffer, mode) │\n", + "│ 272 │ else: │\n", + "│ 273 │ │ if 'w' in mode: │\n", + "│ 274 │ │ │ return _open_buffer_writer(name_or_buffer) │\n", + "│ │\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/torch/serialization.py:252 in │\n", + "│ __init__ │\n", + "│ │\n", + "│ 249 │\n", + "│ 250 class _open_file(_opener): │\n", + "│ 251 │ def __init__(self, name, mode): │\n", + "│ ❱ 252 │ │ super().__init__(open(name, mode)) │\n", + "│ 253 │ │\n", + "│ 254 │ def __exit__(self, *args): │\n", + "│ 255 │ │ self.file_like.close() │\n", + "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n", + "FileNotFoundError: [Errno 2] No such file or directory: \n", + "'../decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin'\n", + "\n", + "During handling of the above exception, another exception occurred:\n", + "\n", + "╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n", + "│ in <module>:16 │\n", + "│ │\n", + "│ 13 │\n", + "│ 14 tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME) │\n", + "│ 15 │\n", + "│ ❱ 16 model = LlamaForCausalLM.from_pretrained( │\n", + "│ 17 │ BASE_MODEL, │\n", + "│ 18 │ load_in_8bit=True, │\n", + "│ 19 │ torch_dtype=torch.float16, │\n", + "│ │\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/modeling_utils.py:28 │\n", + "│ 70 in from_pretrained │\n", + "│ │\n", + "│ 2867 │ │ │ │ mismatched_keys, │\n", + "│ 2868 │ │ │ │ offload_index, │\n", + "│ 2869 │ │ │ │ error_msgs, │\n", + "│ ❱ 2870 │ │ │ ) = cls._load_pretrained_model( │\n", + "│ 2871 │ │ │ │ model, │\n", + "│ 2872 │ │ │ │ state_dict, │\n", + "│ 2873 │ │ │ │ loaded_state_dict_keys, # XXX: rename? │\n", + "│ │\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/modeling_utils.py:32 │\n", + "│ 02 in _load_pretrained_model │\n", + "│ │\n", + "│ 3199 │ │ │ │ # Skip the load for shards that only contain disk-offloaded weights when │\n", + "│ 3200 │ │ │ │ if shard_file in disk_only_shard_files: │\n", + "│ 3201 │ │ │ │ │ continue │\n", + "│ ❱ 3202 │ │ │ │ state_dict = load_state_dict(shard_file) │\n", + "│ 3203 │ │ │ │ │\n", + "│ 3204 │ │ │ │ # Mistmatched keys contains tuples key/shape1/shape2 of weights in the c │\n", + "│ 3205 │ │ │ │ # matching the weights in the model. │\n", + "│ │\n", + "│ /opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/modeling_utils.py:46 │\n", + "│ 2 in load_state_dict │\n", + "│ │\n", + "│ 459 │ │ return torch.load(checkpoint_file, map_location=\"cpu\") │\n", + "│ 460 │ except Exception as e: │\n", + "│ 461 │ │ try: │\n", + "│ ❱ 462 │ │ │ with open(checkpoint_file) as f: │\n", + "│ 463 │ │ │ │ if f.read(7) == \"version\": │\n", + "│ 464 │ │ │ │ │ raise OSError( │\n", + "│ 465 │ │ │ │ │ │ \"You seem to have cloned a repository without having git-lfs ins │\n", + "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n", + "FileNotFoundError: [Errno 2] No such file or directory: \n", + "'../decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin'\n", + "\n" + ], + "text/plain": [ + "\u001b[31m╭─\u001b[0m\u001b[31m──────────────────────────────\u001b[0m\u001b[31m \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m \u001b[0m\u001b[31m───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/\u001b[0m\u001b[1;33mmodeling_utils.py\u001b[0m:\u001b[94m45\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[94m9\u001b[0m in \u001b[92mload_state_dict\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 456 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 457 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m safe_load_file(checkpoint_file) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 458 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mtry\u001b[0m: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 459 \u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m torch.load(checkpoint_file, map_location=\u001b[33m\"\u001b[0m\u001b[33mcpu\u001b[0m\u001b[33m\"\u001b[0m) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 460 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mexcept\u001b[0m \u001b[96mException\u001b[0m \u001b[94mas\u001b[0m e: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 461 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mtry\u001b[0m: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 462 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mwith\u001b[0m \u001b[96mopen\u001b[0m(checkpoint_file) \u001b[94mas\u001b[0m f: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/torch/\u001b[0m\u001b[1;33mserialization.py\u001b[0m:\u001b[94m791\u001b[0m in \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[92mload\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 788 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mif\u001b[0m \u001b[33m'\u001b[0m\u001b[33mencoding\u001b[0m\u001b[33m'\u001b[0m \u001b[95mnot\u001b[0m \u001b[95min\u001b[0m pickle_load_args.keys(): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 789 \u001b[0m\u001b[2m│ │ \u001b[0mpickle_load_args[\u001b[33m'\u001b[0m\u001b[33mencoding\u001b[0m\u001b[33m'\u001b[0m] = \u001b[33m'\u001b[0m\u001b[33mutf-8\u001b[0m\u001b[33m'\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 790 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 791 \u001b[2m│ \u001b[0m\u001b[94mwith\u001b[0m _open_file_like(f, \u001b[33m'\u001b[0m\u001b[33mrb\u001b[0m\u001b[33m'\u001b[0m) \u001b[94mas\u001b[0m opened_file: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 792 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m _is_zipfile(opened_file): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 793 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[2m# The zipfile reader is going to advance the current file position.\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 794 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[2m# If we want to actually tail call to torch.jit.load, we need to\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/torch/\u001b[0m\u001b[1;33mserialization.py\u001b[0m:\u001b[94m271\u001b[0m in \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[92m_open_file_like\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 268 \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 269 \u001b[0m\u001b[94mdef\u001b[0m \u001b[92m_open_file_like\u001b[0m(name_or_buffer, mode): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 270 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mif\u001b[0m _is_path(name_or_buffer): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 271 \u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m _open_file(name_or_buffer, mode) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 272 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94melse\u001b[0m: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 273 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[33m'\u001b[0m\u001b[33mw\u001b[0m\u001b[33m'\u001b[0m \u001b[95min\u001b[0m mode: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 274 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m _open_buffer_writer(name_or_buffer) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/torch/\u001b[0m\u001b[1;33mserialization.py\u001b[0m:\u001b[94m252\u001b[0m in \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[92m__init__\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 249 \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 250 \u001b[0m\u001b[94mclass\u001b[0m \u001b[4;92m_open_file\u001b[0m(_opener): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 251 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92m__init__\u001b[0m(\u001b[96mself\u001b[0m, name, mode): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 252 \u001b[2m│ │ \u001b[0m\u001b[96msuper\u001b[0m().\u001b[92m__init__\u001b[0m(\u001b[96mopen\u001b[0m(name, mode)) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 253 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 254 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mdef\u001b[0m \u001b[92m__exit__\u001b[0m(\u001b[96mself\u001b[0m, *args): \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 255 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m.file_like.close() \u001b[31m│\u001b[0m\n", + "\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n", + "\u001b[1;91mFileNotFoundError: \u001b[0m\u001b[1m[\u001b[0mErrno \u001b[1;36m2\u001b[0m\u001b[1m]\u001b[0m No such file or directory: \n", + "\u001b[32m'../decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin'\u001b[0m\n", + "\n", + "\u001b[3mDuring handling of the above exception, another exception occurred:\u001b[0m\n", + "\n", + "\u001b[31m╭─\u001b[0m\u001b[31m──────────────────────────────\u001b[0m\u001b[31m \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m \u001b[0m\u001b[31m───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n", + "\u001b[31m│\u001b[0m in \u001b[92m\u001b[0m:\u001b[94m16\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m13 \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m14 \u001b[0mtokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m15 \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m16 model = LlamaForCausalLM.from_pretrained( \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m17 \u001b[0m\u001b[2m│ \u001b[0mBASE_MODEL, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m18 \u001b[0m\u001b[2m│ \u001b[0mload_in_8bit=\u001b[94mTrue\u001b[0m, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m19 \u001b[0m\u001b[2m│ \u001b[0mtorch_dtype=torch.float16, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/\u001b[0m\u001b[1;33mmodeling_utils.py\u001b[0m:\u001b[94m28\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[94m70\u001b[0m in \u001b[92mfrom_pretrained\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m2867 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mmismatched_keys, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m2868 \u001b[0m\u001b[2m│ │ │ │ \u001b[0moffload_index, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m2869 \u001b[0m\u001b[2m│ │ │ │ \u001b[0merror_msgs, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m2870 \u001b[2m│ │ │ \u001b[0m) = \u001b[96mcls\u001b[0m._load_pretrained_model( \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m2871 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mmodel, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m2872 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mstate_dict, \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m2873 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mloaded_state_dict_keys, \u001b[2m# XXX: rename?\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/\u001b[0m\u001b[1;33mmodeling_utils.py\u001b[0m:\u001b[94m32\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[94m02\u001b[0m in \u001b[92m_load_pretrained_model\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m3199 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[2m# Skip the load for shards that only contain disk-offloaded weights when\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m3200 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mif\u001b[0m shard_file \u001b[95min\u001b[0m disk_only_shard_files: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m3201 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mcontinue\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m3202 \u001b[2m│ │ │ │ \u001b[0mstate_dict = load_state_dict(shard_file) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m3203 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m3204 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[2m# Mistmatched keys contains tuples key/shape1/shape2 of weights in the c\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m3205 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[2m# matching the weights in the model.\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2;33m/opt/conda/envs/media-reco-env-3-8/lib/python3.8/site-packages/transformers/\u001b[0m\u001b[1;33mmodeling_utils.py\u001b[0m:\u001b[94m46\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[94m2\u001b[0m in \u001b[92mload_state_dict\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 459 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m torch.load(checkpoint_file, map_location=\u001b[33m\"\u001b[0m\u001b[33mcpu\u001b[0m\u001b[33m\"\u001b[0m) \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 460 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94mexcept\u001b[0m \u001b[96mException\u001b[0m \u001b[94mas\u001b[0m e: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 461 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mtry\u001b[0m: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m 462 \u001b[2m│ │ │ \u001b[0m\u001b[94mwith\u001b[0m \u001b[96mopen\u001b[0m(checkpoint_file) \u001b[94mas\u001b[0m f: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 463 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mif\u001b[0m f.read(\u001b[94m7\u001b[0m) == \u001b[33m\"\u001b[0m\u001b[33mversion\u001b[0m\u001b[33m\"\u001b[0m: \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 464 \u001b[0m\u001b[2m│ │ │ │ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mOSError\u001b[0m( \u001b[31m│\u001b[0m\n", + "\u001b[31m│\u001b[0m \u001b[2m 465 \u001b[0m\u001b[2m│ │ │ │ │ │ \u001b[0m\u001b[33m\"\u001b[0m\u001b[33mYou seem to have cloned a repository without having git-lfs ins\u001b[0m \u001b[31m│\u001b[0m\n", + "\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n", + "\u001b[1;91mFileNotFoundError: \u001b[0m\u001b[1m[\u001b[0mErrno \u001b[1;36m2\u001b[0m\u001b[1m]\u001b[0m No such file or directory: \n", + "\u001b[32m'../decapoda-research/llama-7b-hf/pytorch_model-00001-of-00033.bin'\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import torch\n", + "from transformers import GenerationConfig, LlamaTokenizer, LlamaForCausalLM\n", + "from peft import PeftModel, PeftConfig\n", + "\n", + "\n", + "MODEL_NAME = \"../\"\n", + "BASE_MODEL = \"../decapoda-research/llama-7b-hf\"\n", + "# MODEL_NAME = f\"lora-alpaca/conversations/GPU/{MODEL_NAME}\"\n", + "# MODEL_NAME = \"chainyo/alpaca-lora-7b\"\n", + "# MODEL_NAME = \"decapoda-research/llama-7b-hf\"\n", + "\n", + "config = PeftConfig.from_pretrained(MODEL_NAME)\n", + "\n", + "tokenizer = LlamaTokenizer.from_pretrained(MODEL_NAME)\n", + "\n", + "model = LlamaForCausalLM.from_pretrained(\n", + " BASE_MODEL,\n", + " load_in_8bit=True,\n", + " torch_dtype=torch.float16,\n", + " device_map=\"auto\",\n", + ")\n", + "\n", + "# model = PeftModel.from_pretrained(model, MODEL_NAME)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "71dfae0f", + "metadata": {}, + "outputs": [], + "source": [ + "model.eval()\n", + "if torch.__version__ >= \"2\":\n", + " model = torch.compile(model)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "10372ae3", + "metadata": {}, + "outputs": [], + "source": [ + "generation_config = GenerationConfig(\n", + " temperature=0.2,\n", + " top_p=0.75,\n", + " top_k=40,\n", + " num_beams=4,\n", + " max_new_tokens=32,\n", + " repetition_penalty=1.5,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a84a4f9e", + "metadata": {}, + "outputs": [], + "source": [ + "instruction = \"I have two pieces of apples and 3 pieces of oranges. How many pieces of fruits do I have?\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "65117ac7", + "metadata": {}, + "outputs": [], + "source": [ + "instruction = \"What is the capital city of Greece and with which countries does Greece border?\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2ff7a5e5", + "metadata": {}, + "outputs": [], + "source": [ + "instruction = \"How can I cook Adobo?\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b2b504da", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9cba7db1", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "af3a477a", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "44fdd7ee", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Which are the tags of the following article: 'A year ago, Russia invaded Ukraine in a major escalation of the Russo-Ukrainian War, which had begun in 2014. The invasion has resulted in thousands of deaths, and instigated Europe's largest refugee crisis since World War II.\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "1f3a96aa", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Translate the following text from English to Greek: 'My name is George. I am 22 years old and I live with my parents.'\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "b87f4120", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Ποιά είναι η πρωτεύουσα της Ελλάδας?\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "520edf24", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a2fdfc6b", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Translate the following text from Italian to English: 'Alla vigilia della sfida contro l'Inter, Luciano Spalletti risponde alle recenti parole del presidente De Laurentiis che ha messo in dubbio il suo futuro sulla panchina del Napoli.'\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6b87cfde", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"What is the capital city of Greece and with which countries does Greece border?\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "08f25326", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"I have two oranges and 3 apples. How many pieces of fruits I have in total?\"\n", + "input_ctxt = \"Question Answering\" # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "218815c4", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Which are the tags of the following article: 'Prozess in Winterthur: Handwerker (69) wegen uraltem Sex-Heftli vor Gericht. Ein 69-jähriger Handwerker stand in Winterthur vor Gericht, weil bei ihm ein 35 Jahre altes Heftchen mit explizitem Inhalt gefunden wurde. Die Anklage scheiterte. Die Polizei führte bei einem Winterthurer eine Hausdurchsuchung durch, nachdem US-Behörden den Schweizer Behörden einen Hinweis auf ein verbotenes pornografisches Bild gaben. Allerdings fand sich auf den elektronischen Geräten des Mannes nicht der kleinste Hinweis auf weitere Bilder oder Videos im Zusammenhang mit Kinderpornografie, Sex mit Tieren oder mit Gewaltdarstellungen. Das Strafverfahren wurde eingestellt. «Jung und froh mit nacktem Po». Aber: Bei der Hausdurchsuchung stellten die Beamten ein 35 Jahre altes Sexheftli des Orion-Verlags in den Lagerräumen des Handwerkers sicher, wie der «Tages-Anzeiger» berichtet. Das Heftchen «Jung und froh mit nacktem Po» enthielt auf mehr als zehn Seiten ganzseitige Fotos nackter Mädchen und Jungen im Alter von drei bis fünfzehn Jahren.'?\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4fdd7591", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Which are the tags of the following article: 'For those now grappling with Alzheimer’s, lecanemab holds out the promise of slowing the disease’s progress. Are the modest benefits worth the risks? (C1)\\nAfter many decades of little or no progress in treating the dementia associated with Alzheimer’s, a new drug now offers hope to patients and caregivers. Lecanemab, announced late last month, was found in clinical trials to slow cognitive decline in early-stage Alzheimer’s patients. “It’s an extremely encouraging result,” says Dr. David Wolk, co-director of the University of Pennsylvania’s Penn Memory Center'?\"\n", + "input_ctxt = \"Question Answering\" # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0ff82833", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Which characteristic is least likely to be affected by an individual's environment? (A) height (B) weight (C) skin color (D) eye color\"\n", + "input_ctxt = \"Tags\" # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "840e70c5", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"A student mixed some yellow sulfur powder with some iron filings. She was able to take the iron out of the sulfur by using a magnet. She then remixed the iron and sulfur in a test tube and heated it. After it cooled, she removed the substance from the test tube but could not separate the iron from the sulfur using the magnet. Which type of change occurred in the material when it was heated? (A) a physical change because the iron reacted with the sulfur (B) a chemical change because a new substance was formed (C) a physical change because a compound was formed (D) a chemical change because a magnet had to be used\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "54139a84", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Translate the following from English to Greek: 'My name is George. I am 22 years old and I live with my parents.'\"\n", + "input_ctxt = \"Question Answering\" # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c88de39f", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Translate the following from English to Spanish: 'My name is George. I am 22 years old and I live with my parents.'\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fbccda31", + "metadata": {}, + "outputs": [], + "source": [ + "%%time\n", + "\n", + "instruction = \"Translate the following from English to Tagalog: 'I love you. How is your day? Have you eaten?'\"\n", + "input_ctxt = None # For some tasks, you can provide an input context to help the model generate a better response.\n", + "\n", + "prompt = generate_prompt(instruction, input_ctxt)\n", + "input_ids = tokenizer(prompt, return_tensors=\"pt\").input_ids\n", + "input_ids = input_ids.to(model.device)\n", + "\n", + "with torch.no_grad():\n", + " outputs = model.generate(\n", + " input_ids=input_ids,\n", + " generation_config=generation_config,\n", + " return_dict_in_generate=True,\n", + " output_scores=True,\n", + " )\n", + "\n", + "response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)\n", + "print(response)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "aa6e355b", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a6df3c6d", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python [conda env:media-reco-env-3-8]", + "language": "python", + "name": "conda-env-media-reco-env-3-8-py" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.0" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/pytorch_model_trainer_llama_7b.bin b/pytorch_model_trainer_llama_7b.bin deleted file mode 100644 index 1c4a7caed92c23e190db02342f530675bb29a50c..0000000000000000000000000000000000000000 --- a/pytorch_model_trainer_llama_7b.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a62f72199fe4ec92a16c35ee541c2346b88fac542dcc07be319aab6d078956cd -size 7539796821