diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a91e94e9eb5ba5fa16734d970172acf304f93dae --- /dev/null +++ b/config.json @@ -0,0 +1,74 @@ +{ + "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct", + "architectures": [ + "LlamaForSequenceClassification" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "id2label": { + "0": "token activation 0", + "1": "token activation 1", + "2": "token activation 2", + "3": "token activation 3", + "4": "token activation 4", + "5": "token activation 5", + "6": "token activation 6", + "7": "token activation 7", + "8": "token activation 8", + "9": "token activation 9", + "10": "token activation 10", + "11": "token activation 11", + "12": "token activation 12", + "13": "token activation 13", + "14": "token activation 14", + "15": "token activation 15", + "16": "token activation 16", + "17": "token activation 17", + "18": "token activation 18", + "19": "token activation 19" + }, + "initializer_range": 0.02, + "intermediate_size": 28672, + "label2id": { + "token activation 0": 0, + "token activation 1": 1, + "token activation 10": 10, + "token activation 11": 11, + "token activation 12": 12, + "token activation 13": 13, + "token activation 14": 14, + "token activation 15": 15, + "token activation 16": 16, + "token activation 17": 17, + "token activation 18": 18, + "token activation 19": 19, + "token activation 2": 2, + "token activation 3": 3, + "token activation 4": 4, + "token activation 5": 5, + "token activation 6": 6, + "token activation 7": 7, + "token activation 8": 8, + "token activation 9": 9 + }, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.48.2", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/model-00001-of-00061.safetensors b/model-00001-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85357281120571a20aa2b6a75cc6609195a51ecb --- /dev/null +++ b/model-00001-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d2d50294648f6fc8a0b227e89e2c83ddd8b93bc9b30225cd6b07d7383c9eef +size 4806672984 diff --git a/model-00002-of-00061.safetensors b/model-00002-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f24b0f8a871ddf0b30e99cce8b989855b16385f6 --- /dev/null +++ b/model-00002-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:706288d67528b9d7f8bc1241e59381ba945b94b8f10dea96300e5ad85a7d6113 +size 4362142864 diff --git a/model-00003-of-00061.safetensors b/model-00003-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d2c0d7a057fbab1ae54ba7053fac8a5fb8ae307 --- /dev/null +++ b/model-00003-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf3cbb1f5dbe5679cd00fe526f202b52a2ae5590c4fcdba108e5470c44440e7 +size 4362142864 diff --git a/model-00004-of-00061.safetensors b/model-00004-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54f4cf75e2fb8d0fd484017b0f1f1e6da3f87089 --- /dev/null +++ b/model-00004-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fd2aab24f6673dc2b6caa3c3a62ff647baa81af2f3ba6234f66c4f8433045f +size 4966188864 diff --git a/model-00005-of-00061.safetensors b/model-00005-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..197ec96bd8ceab802e42eef4c58a7cde7271a22b --- /dev/null +++ b/model-00005-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a74adee271be6520954bb732c2a0b65cd35a8f724ad09ec5b00bb1f95ac3875 +size 4362142864 diff --git a/model-00006-of-00061.safetensors b/model-00006-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91d654e1999e8274ae4c8e03567bc25e44bd664e --- /dev/null +++ b/model-00006-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8959c4c63ceb1b9aaf62e0b0c79f1da148b2d1d56f0d748aed463016553bfe16 +size 4362142864 diff --git a/model-00007-of-00061.safetensors b/model-00007-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cc3cdb8566560439c1d1f3b7954589ff3d4b3f6 --- /dev/null +++ b/model-00007-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f8bc93bf3634eb3731e320d0bee288753cb15a80bf97840a3179c1681bbfb3 +size 4966188864 diff --git a/model-00008-of-00061.safetensors b/model-00008-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4eed330afb4d75202e16be8e6864a59c32b23bc4 --- /dev/null +++ b/model-00008-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d031f46300a51421176328d63157caeb19519afe6c4f48e86415b90dd404865d +size 4362142864 diff --git a/model-00009-of-00061.safetensors b/model-00009-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e52d9af30bf0031235eab62fe74c44e848ec12d6 --- /dev/null +++ b/model-00009-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2249433ae3beace2923bd6a9819c33fee747bb078c2399ed0b9086b74dc89d +size 4362142880 diff --git a/model-00010-of-00061.safetensors b/model-00010-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6c5238c0be8a6b48147c27f4d3fe0ad98b97d96 --- /dev/null +++ b/model-00010-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf667a11eb07e0bef46c73303eb8064e58d97475c1c5e46627c3a50549e25816 +size 4966188880 diff --git a/model-00011-of-00061.safetensors b/model-00011-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..479755869bdcb6ea6e1db6b9334ebbd9a0fd7b01 --- /dev/null +++ b/model-00011-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9515902f4370a1de339ee9af1a3f1ef3275b99a1b24ff0743bc25664f2e4f5f3 +size 4362142872 diff --git a/model-00012-of-00061.safetensors b/model-00012-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..38bd319c6bf4b2b88d0e3ce276eda8ee0c4a19f9 --- /dev/null +++ b/model-00012-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c4cab7e8f483cd15af16c130e41bf61919645fa34c3494297a5544b62e2efd +size 4362142872 diff --git a/model-00013-of-00061.safetensors b/model-00013-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..65e3724ce2ea0ee09717e1f4b9e4fb6561188a1b --- /dev/null +++ b/model-00013-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1f40d779bc4a87af3c194a80abbcb9766fc8c33bd25ac5ff8fc39b851570f2 +size 4966188880 diff --git a/model-00014-of-00061.safetensors b/model-00014-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..340dd9e1c412a7df93dc257c8abfa41bcdd16d33 --- /dev/null +++ b/model-00014-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeb0076328078d6c822450b3959ee9009f1625e4ff466aa77d7dcdde7c5a553 +size 4362142872 diff --git a/model-00015-of-00061.safetensors b/model-00015-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74a90076bd3be49ebc4643d7210e176958610520 --- /dev/null +++ b/model-00015-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7738466ad72cb7a045290f47a103ccb028df03981a77eaac4df05e197b81a13 +size 4362142872 diff --git a/model-00016-of-00061.safetensors b/model-00016-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4e0809fa8cc2e0815020f05e5f812a0ee144579 --- /dev/null +++ b/model-00016-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c765dca3926b0689847c78bed92bc23b3cca3eb2311fcf766f814b0d2492302 +size 4966188880 diff --git a/model-00017-of-00061.safetensors b/model-00017-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6198e24fb2579a3a91d0c374365c4ceb59d6f3e6 --- /dev/null +++ b/model-00017-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e0ab78c85d98cbeb479d890165ec98274a2a32ebc19f77656bb91148358ec2 +size 4362142872 diff --git a/model-00018-of-00061.safetensors b/model-00018-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..252c64bebe955eed6343c5e0ba207f8c8353c4ac --- /dev/null +++ b/model-00018-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e71d58dd41197fad9511445302b55329d50b570b70dadd867bf32238278602ec +size 4362142872 diff --git a/model-00019-of-00061.safetensors b/model-00019-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2db10ae07ea90a0f12b7ce1bd0fdd424dbc1ae9d --- /dev/null +++ b/model-00019-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeabb10cc6d0b37b8ca5a1d8a75ccae4c523a00d1bbc22fd23cad424ab7fe391 +size 4966188880 diff --git a/model-00020-of-00061.safetensors b/model-00020-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e59ef6dc8547ae5e22cc252ba54fde77a19427a6 --- /dev/null +++ b/model-00020-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878d2467de0db2e32a1157e68a63428acdb6edd6203f80a9b9ab847a8de65d31 +size 4362142872 diff --git a/model-00021-of-00061.safetensors b/model-00021-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..617c85181b7fe3587c352335d0cc154f1fad42b5 --- /dev/null +++ b/model-00021-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29010df87ff2746db05f9108244c2aa745c12ce7fa03700bea554d9dda18cb56 +size 4362142872 diff --git a/model-00022-of-00061.safetensors b/model-00022-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b8a5c50196f7854e8da8ac3e684f62932717c73 --- /dev/null +++ b/model-00022-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b8647e992d4cdc8ad70c18c4f4c9466e8edaa2ea0b9d3cfee0ea78f089d75f +size 4966188880 diff --git a/model-00023-of-00061.safetensors b/model-00023-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29f5da7b4f89c3f3ef0f8ece629dd1496679ea30 --- /dev/null +++ b/model-00023-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce7b41b732c0d01bd233229203693698a86682eb7955c56e8ac707548ccec32 +size 4362142872 diff --git a/model-00024-of-00061.safetensors b/model-00024-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cf49c0a0737bf989f01cb394d93aefbc9f28d81 --- /dev/null +++ b/model-00024-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fafcd2051b570459da98df18abccf8ceb870b3e40d9bfe1f02e80b6f85efb4ce +size 4362142872 diff --git a/model-00025-of-00061.safetensors b/model-00025-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58f5a163d4d05784ff8009d3d6fa38357c6c0a27 --- /dev/null +++ b/model-00025-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2aee706f2c96b40bb3a6a105d28f722a9dc71030289af3346dedccc124f2546 +size 4966188880 diff --git a/model-00026-of-00061.safetensors b/model-00026-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..517a7168e22e05b43f72d5a320e0ac4c47262ae4 --- /dev/null +++ b/model-00026-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a8abc52e6f67e9c21056305c690092441b3417a318644da65abd4b23575cb7 +size 4362142872 diff --git a/model-00027-of-00061.safetensors b/model-00027-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cb15606cdc21caf8bcc564ef309cb000b6caa82 --- /dev/null +++ b/model-00027-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdf9602328a11df70e3f2fd39f9c09926d2126663549159854066e16e46c4e5 +size 4362142872 diff --git a/model-00028-of-00061.safetensors b/model-00028-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef163b7f131a6147c061c2a91b964414b6914cbd --- /dev/null +++ b/model-00028-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f2417ede400daca3075769a10be35dd1e3991b2b4e83bc8843ff518bd14fc4 +size 4966188880 diff --git a/model-00029-of-00061.safetensors b/model-00029-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f5411b564717dfc14d4608b0be9996eee741e9f4 --- /dev/null +++ b/model-00029-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b60db2f582fc2095888a90c115fba11d80c9613fc04d6732415ce89ab1f988 +size 4362142872 diff --git a/model-00030-of-00061.safetensors b/model-00030-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..900bd6032d3862a08808ddb711862d63321e5861 --- /dev/null +++ b/model-00030-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa67f89d10d96e5334d22153bc797404ead5b8d72562c55298bf9ada7d28493 +size 4362142872 diff --git a/model-00031-of-00061.safetensors b/model-00031-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a7440211b3fdee32a48fef1e1b340e6445b8527 --- /dev/null +++ b/model-00031-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:161618c0c936d386e7cd9f950d3c9a94342c2a012171cbccf49a4451b5892b89 +size 4966188880 diff --git a/model-00032-of-00061.safetensors b/model-00032-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c917e59fdb496801598a6c52d93355181ea52e16 --- /dev/null +++ b/model-00032-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700acb257e021d70af9e90b1a13503616912c622783584b653094da389463711 +size 4362142872 diff --git a/model-00033-of-00061.safetensors b/model-00033-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e454a931d0f32177636ece5f4b9a0bd97acb4337 --- /dev/null +++ b/model-00033-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff234701ee36cf3ce9cbf7062a190a3a23c6c98746083defed2547d72d68b636 +size 4362142872 diff --git a/model-00034-of-00061.safetensors b/model-00034-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8aa3b31b4e7e494ea237026dc88121759d8295a6 --- /dev/null +++ b/model-00034-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77030dc229ea74eec9410ca7e56f8deae4b39246a867a235efd8b827a955fa52 +size 4966188880 diff --git a/model-00035-of-00061.safetensors b/model-00035-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04942711513b24121113d71e3bc68afb801b0864 --- /dev/null +++ b/model-00035-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f97934e6da54e800ddec0a851adbe94da76924fbee1630a0cfa6ed2d945079 +size 4362142872 diff --git a/model-00036-of-00061.safetensors b/model-00036-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1cae17fce97032217ec52f9e4d25982bb04df36d --- /dev/null +++ b/model-00036-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6096475a651ec2f713921131166f8b797a4c8dbd3153fb64b518f3fe0350d53 +size 4362142872 diff --git a/model-00037-of-00061.safetensors b/model-00037-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6945cbc7d6ffd4582645cf8c46145dd6643b9222 --- /dev/null +++ b/model-00037-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4013d07353082728536d0d9a1f014a1563dcdbb1820a01267c3e0f6a1742d98 +size 4966188880 diff --git a/model-00038-of-00061.safetensors b/model-00038-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d3256a934f11fc765dd9d9513ba16b43d98379b --- /dev/null +++ b/model-00038-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14aebd14ed4da14d5fcb85f4bb1b6bf1fc1385bad791e9530fa878e9366b6040 +size 4362142872 diff --git a/model-00039-of-00061.safetensors b/model-00039-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b25ac2df6a058fd22bd0d27478b12968b53cd079 --- /dev/null +++ b/model-00039-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3043ca41bac40bf6c05056fe905cf2b8585eac0ce1a40e9224adc935d652816a +size 4362142872 diff --git a/model-00040-of-00061.safetensors b/model-00040-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fcef70d3923af40c73f7a7c484d068738b38c1b --- /dev/null +++ b/model-00040-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7946d1c7ed090749761943ee099e051d1067f2a6e11f4dc27bef5a48f6d675 +size 4966188880 diff --git a/model-00041-of-00061.safetensors b/model-00041-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6069ec2e592b736bc49abfc01918646f15b5c55 --- /dev/null +++ b/model-00041-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff60b3d9b6aa5e8a3d4402d98d4a69027e78d4f5282ec510a675c209d0464c3 +size 4362142872 diff --git a/model-00042-of-00061.safetensors b/model-00042-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..062bbc4b1b966cd4e9e74fc6b9beaacd2c8e5db6 --- /dev/null +++ b/model-00042-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a45e1c66c817b797739f9305bdd237ef347a1ec21e24700780b1b299a56717 +size 4362142872 diff --git a/model-00043-of-00061.safetensors b/model-00043-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ab8030c2b7ad647719de3a5956a4b3261dc7a91 --- /dev/null +++ b/model-00043-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89401423308c0a7c2b56d478a1589435f33a3b31f3f402cd78a652eb1dd470b3 +size 4966188880 diff --git a/model-00044-of-00061.safetensors b/model-00044-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..205f6d84ae857002211b2b4b71fc205888565836 --- /dev/null +++ b/model-00044-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1e0f01b09034312ca5884ed4258f883eb3aef31770db203a08634f1c7306350 +size 4362142872 diff --git a/model-00045-of-00061.safetensors b/model-00045-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f50f31afb2ee5b86b5df2b7bc4539d7bd85523f0 --- /dev/null +++ b/model-00045-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:814c3d7b32af717dde6d2da77fc905d9ddf6dc5c20d992ee1ffe1b2ddcbf9283 +size 4362142872 diff --git a/model-00046-of-00061.safetensors b/model-00046-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22f19c3ab116b5d5c59cc754706d2887b4c199f1 --- /dev/null +++ b/model-00046-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfba1888a209b37476a8467043a558fa904cd717d42a75311ee8371d1e3d6803 +size 4966188880 diff --git a/model-00047-of-00061.safetensors b/model-00047-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7aef7610e3a35af4170fc51e0e76fecce77f8cad --- /dev/null +++ b/model-00047-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d713bc654e9779cedd7446f30f01d275b59447f8732a89e5816b637b6c7868 +size 4362142872 diff --git a/model-00048-of-00061.safetensors b/model-00048-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9514c87c2526fe6b7f66df80344b46431f79222d --- /dev/null +++ b/model-00048-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc94c9b2fb6fa49febe5dc6c701a25c7c3463a17a8dd09f6342b38094bfc685b +size 4362142872 diff --git a/model-00049-of-00061.safetensors b/model-00049-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78575bee22a612abb1f4db79f990e143633ed9f9 --- /dev/null +++ b/model-00049-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7271c8d5c19b40eb278b88abb093197cb1e90d6594576ba54304e074336c6119 +size 4966188880 diff --git a/model-00050-of-00061.safetensors b/model-00050-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1710a26ba7d4bfe8ca6c15ff7e3e997be5633c8b --- /dev/null +++ b/model-00050-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c92bdeace883f65625a9a6b135725a2e85010a7440a0e51c6b1193240b461d8 +size 4362142872 diff --git a/model-00051-of-00061.safetensors b/model-00051-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad39309f08bd89ebf7a08d975f1f05a906bf83ec --- /dev/null +++ b/model-00051-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8beac69602b2ec02547e525847df0b1272c26a1d216d05b69d426e31bf250f +size 4362142872 diff --git a/model-00052-of-00061.safetensors b/model-00052-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..164a978c9e552072f9f959cce4e9e49fe4e1c04b --- /dev/null +++ b/model-00052-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205dc990014e7046a9823d006367f21e0f73264596f35a85e8a2f8e82a0c6c40 +size 4966188880 diff --git a/model-00053-of-00061.safetensors b/model-00053-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f53b8b7dad7bfc50c29526c945caff0a881b966 --- /dev/null +++ b/model-00053-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e9a8154e80de237548e5ad93a88b01fca1a105fd9c571adc2f9378e594109dc +size 4362142872 diff --git a/model-00054-of-00061.safetensors b/model-00054-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0df4154bb3b8b74d6a73a116cd14025a4f264daf --- /dev/null +++ b/model-00054-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b192ed9c4ed1aaa727d56c3602ec6bdf1d493979285454b8d702756c94d82e0e +size 4362142872 diff --git a/model-00055-of-00061.safetensors b/model-00055-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d5d1164f85d403266b9c36d321578e3f89ad65e --- /dev/null +++ b/model-00055-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfd0bbc06b889d7c3b2fd69813788e1b619bb1ec65d41bc4fa9f21ab5699673 +size 4966188880 diff --git a/model-00056-of-00061.safetensors b/model-00056-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb971654719494f6891bbab3c6f1f4c6cb34c05a --- /dev/null +++ b/model-00056-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053d3fa0c891b7e6c8be1ba2a00aeda6960c599f927e12c9480eb7d6a5b28e47 +size 4362142872 diff --git a/model-00057-of-00061.safetensors b/model-00057-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..619e75ddd9e9056bafae67c2619f93cd52f66dbc --- /dev/null +++ b/model-00057-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c9341117b3b3c401dfa9e49e4e4e1632e4e05d55753c4506c6f9a7b1dcb66c +size 4362142872 diff --git a/model-00058-of-00061.safetensors b/model-00058-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..538352af939df9744692c84788a72f45c54480f0 --- /dev/null +++ b/model-00058-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79f8cc53edd9459380a2f3175c9f11390732483b5baea4632b2b6e50c500313 +size 4966188880 diff --git a/model-00059-of-00061.safetensors b/model-00059-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4fb6b69ff4e4e52c2109759e553402dbf28f28b --- /dev/null +++ b/model-00059-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099d438e1db64e8dc8c137b65c9ffe4dcb6e464b8fce37b0e722b8e17719b702 +size 4362142872 diff --git a/model-00060-of-00061.safetensors b/model-00060-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdb8dbcdf45c5c34239a31c067718d03843b1b36 --- /dev/null +++ b/model-00060-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf75f0cebe034f6e19493065118c7e0a28f942d1e64f9b25e17eab96441e7d9 +size 4362142872 diff --git a/model-00061-of-00061.safetensors b/model-00061-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4cf730f408734e0b35bf23e202eac93f827ccbc9 --- /dev/null +++ b/model-00061-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31b6e450e74a7939e7eb23c929039bd12539f47bbf40ba33e540a12605eed21 +size 4362896944 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5cc38e044f6dfac806b9be1ff2da18336b304a09 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 278012788736 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00061.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00061.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00061.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00061.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00061.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.10.input_layernorm.weight": "model-00010-of-00061.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00061.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.11.input_layernorm.weight": "model-00010-of-00061.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00061.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.input_layernorm.weight": "model-00011-of-00061.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00061.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.13.input_layernorm.weight": "model-00012-of-00061.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00061.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.14.input_layernorm.weight": "model-00013-of-00061.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00061.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.15.input_layernorm.weight": "model-00013-of-00061.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00013-of-00061.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.input_layernorm.weight": "model-00014-of-00061.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00061.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.17.input_layernorm.weight": "model-00015-of-00061.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00015-of-00061.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.18.input_layernorm.weight": "model-00016-of-00061.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00016-of-00061.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.19.input_layernorm.weight": "model-00016-of-00061.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00016-of-00061.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00061.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00061.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.20.input_layernorm.weight": "model-00017-of-00061.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00017-of-00061.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.21.input_layernorm.weight": "model-00018-of-00061.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00061.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.22.input_layernorm.weight": "model-00019-of-00061.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00019-of-00061.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.23.input_layernorm.weight": "model-00019-of-00061.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00061.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.input_layernorm.weight": "model-00020-of-00061.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00061.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.25.input_layernorm.weight": "model-00021-of-00061.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00061.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.26.input_layernorm.weight": "model-00022-of-00061.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00061.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.27.input_layernorm.weight": "model-00022-of-00061.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00022-of-00061.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.input_layernorm.weight": "model-00023-of-00061.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00061.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.29.input_layernorm.weight": "model-00024-of-00061.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00024-of-00061.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00061.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00061.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.30.input_layernorm.weight": "model-00025-of-00061.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00025-of-00061.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.31.input_layernorm.weight": "model-00025-of-00061.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00061.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.input_layernorm.weight": "model-00026-of-00061.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00026-of-00061.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.33.input_layernorm.weight": "model-00027-of-00061.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00027-of-00061.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.34.input_layernorm.weight": "model-00028-of-00061.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00028-of-00061.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.35.input_layernorm.weight": "model-00028-of-00061.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00028-of-00061.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.input_layernorm.weight": "model-00029-of-00061.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00029-of-00061.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.37.input_layernorm.weight": "model-00030-of-00061.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00030-of-00061.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.38.input_layernorm.weight": "model-00031-of-00061.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00031-of-00061.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.39.input_layernorm.weight": "model-00031-of-00061.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00031-of-00061.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00061.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00061.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.40.input_layernorm.weight": "model-00032-of-00061.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00032-of-00061.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.41.input_layernorm.weight": "model-00033-of-00061.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00033-of-00061.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.42.input_layernorm.weight": "model-00034-of-00061.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00034-of-00061.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.43.input_layernorm.weight": "model-00034-of-00061.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00034-of-00061.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.input_layernorm.weight": "model-00035-of-00061.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00035-of-00061.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.45.input_layernorm.weight": "model-00036-of-00061.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00036-of-00061.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.46.input_layernorm.weight": "model-00037-of-00061.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00037-of-00061.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.47.input_layernorm.weight": "model-00037-of-00061.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00037-of-00061.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.input_layernorm.weight": "model-00038-of-00061.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00038-of-00061.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.49.input_layernorm.weight": "model-00039-of-00061.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00039-of-00061.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00061.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00061.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.50.input_layernorm.weight": "model-00040-of-00061.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00040-of-00061.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.51.input_layernorm.weight": "model-00040-of-00061.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00040-of-00061.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.input_layernorm.weight": "model-00041-of-00061.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00041-of-00061.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.53.input_layernorm.weight": "model-00042-of-00061.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00042-of-00061.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.54.input_layernorm.weight": "model-00043-of-00061.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00043-of-00061.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.55.input_layernorm.weight": "model-00043-of-00061.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00043-of-00061.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.input_layernorm.weight": "model-00044-of-00061.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00044-of-00061.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.57.input_layernorm.weight": "model-00045-of-00061.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00045-of-00061.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.58.input_layernorm.weight": "model-00046-of-00061.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00046-of-00061.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.59.input_layernorm.weight": "model-00046-of-00061.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00046-of-00061.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00061.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00061.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.60.input_layernorm.weight": "model-00047-of-00061.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00047-of-00061.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.61.input_layernorm.weight": "model-00048-of-00061.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00048-of-00061.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.62.input_layernorm.weight": "model-00049-of-00061.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00049-of-00061.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.63.input_layernorm.weight": "model-00049-of-00061.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00049-of-00061.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.input_layernorm.weight": "model-00050-of-00061.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00050-of-00061.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.65.input_layernorm.weight": "model-00051-of-00061.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00051-of-00061.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.66.input_layernorm.weight": "model-00052-of-00061.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00052-of-00061.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.67.input_layernorm.weight": "model-00052-of-00061.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00052-of-00061.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.input_layernorm.weight": "model-00053-of-00061.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00053-of-00061.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.69.input_layernorm.weight": "model-00054-of-00061.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00054-of-00061.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00061.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00061.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.70.input_layernorm.weight": "model-00055-of-00061.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00055-of-00061.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.71.input_layernorm.weight": "model-00055-of-00061.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00061.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.input_layernorm.weight": "model-00056-of-00061.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00061.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.73.input_layernorm.weight": "model-00057-of-00061.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00057-of-00061.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.74.input_layernorm.weight": "model-00058-of-00061.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00058-of-00061.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.75.input_layernorm.weight": "model-00058-of-00061.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00061.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.input_layernorm.weight": "model-00059-of-00061.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00061.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.77.input_layernorm.weight": "model-00060-of-00061.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00060-of-00061.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.78.input_layernorm.weight": "model-00061-of-00061.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00061-of-00061.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.79.input_layernorm.weight": "model-00061-of-00061.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00061.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00061.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00061.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00061.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00061.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00061.safetensors", + "model.norm.weight": "model-00061-of-00061.safetensors", + "score.weight": "model-00061-of-00061.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..02ee80b6196926a5ad790a004d9efd6ab1ba6542 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,16 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..873ad336576e40eb8feeffe47d5a427268f8151e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "tokenizer_class": "PreTrainedTokenizerFast" +}