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..a165eef0d8e69b60335b5f36b9f40d561ea41558 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "CohereForAI/c4ai-command-r-plus", + "architectures": [ + "CohereForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 5, + "eos_token_id": 255001, + "hidden_act": "silu", + "hidden_size": 12288, + "initializer_range": 0.02, + "intermediate_size": 33792, + "layer_norm_eps": 1e-05, + "logit_scale": 0.8333333333333334, + "max_position_embeddings": 8192, + "model_max_length": 131072, + "model_type": "cohere", + "num_attention_heads": 96, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "pad_token_id": 0, + "rope_theta": 75000000.0, + "torch_dtype": "float16", + "transformers_version": "4.39.2", + "use_cache": true, + "use_qk_norm": true, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a82e281bc64b282cfa3862884f4343c588d6b0cf --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 5, + "eos_token_id": 255001, + "pad_token_id": 0, + "transformers_version": "4.39.2" +} diff --git a/model-00001-of-00044.safetensors b/model-00001-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e22135e84ef8bf734a50ac76bd3139e57327d88 --- /dev/null +++ b/model-00001-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee321057203258a9356a5fe30deab557b0b7070d1da93153b5dddd66328cf000 +size 6291456144 diff --git a/model-00002-of-00044.safetensors b/model-00002-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dca3b785b89fc2bab5d0687fac198cf3b63a5b93 --- /dev/null +++ b/model-00002-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bee807706b432d9193f4ed757a9703c31cf10d500c5eccd02e1dc47e3735f55 +size 4630537720 diff --git a/model-00003-of-00044.safetensors b/model-00003-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30e5d25ff5013e0a06620332f1bf37354790abc5 --- /dev/null +++ b/model-00003-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181a0766d4d286733b647c403998a397ed4cbd4ece79c43b6a70f5625a6401a8 +size 4806722824 diff --git a/model-00004-of-00044.safetensors b/model-00004-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c59b25f86814d63df2a7504b7b3a49f915a4e035 --- /dev/null +++ b/model-00004-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae19ac0af5ac560d4cd07c8a9f417dde6bca96a54325c5972d76b675e2612c4 +size 4630537720 diff --git a/model-00005-of-00044.safetensors b/model-00005-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..84957d8c8ea7c3950ab53f168a4870dfabb2f7b8 --- /dev/null +++ b/model-00005-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5a75ba22762589927eedba80efd5227788ff96e74a5ec6a35668e608a1f264 +size 4806722824 diff --git a/model-00006-of-00044.safetensors b/model-00006-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..340408d5305ee08cf3057669ad73b21b50a8475d --- /dev/null +++ b/model-00006-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2623c10ef7716b94ce87a6cf391f3339fa39ee11b29fd3cca536a96fff90c0c +size 4630537720 diff --git a/model-00007-of-00044.safetensors b/model-00007-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62929bd8a942f6df3fc4d3f06958e4c666971a3c --- /dev/null +++ b/model-00007-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e5f72e84806ac31336eb3c74061cf0570f1da7d746b3579e5f502386609f91 +size 4806722824 diff --git a/model-00008-of-00044.safetensors b/model-00008-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d12c0ad604c5d874269bd75c08050f60dbc1e0d9 --- /dev/null +++ b/model-00008-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45101ec06daeb795c7e3da63a88ce79b1213b5f050574dc941f238072ed7ccbd +size 4630537736 diff --git a/model-00009-of-00044.safetensors b/model-00009-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..089b7eb5fc46189aefe5d4e0a2137be008eeba05 --- /dev/null +++ b/model-00009-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d0b2129278e79d93ffd275bb1ecccb13f384f4f0ee85a2c6deccba607706b2 +size 4806722832 diff --git a/model-00010-of-00044.safetensors b/model-00010-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76cb99143ec0942617530ad826f2cca610a4b8c3 --- /dev/null +++ b/model-00010-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a208a5304f49e75c2fb1b3c854f47f5caf7aef648fa1dd1c819d7d2ec1ad040c +size 4630537736 diff --git a/model-00011-of-00044.safetensors b/model-00011-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e92b0754bb82028ea5f37ee809d892a9f80e180 --- /dev/null +++ b/model-00011-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:434dc5c28c8bcd06f8d3d1916147eaab2f60054b5a2d7ec4502eb00b9eb9963e +size 4806722832 diff --git a/model-00012-of-00044.safetensors b/model-00012-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2f1474db1adf187f716b94aeb1a34f0b187842c --- /dev/null +++ b/model-00012-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aacdbf0de99dadd1168915434b8fc85def50eaa1f92ad3d3944196bfb0b7c7bb +size 4630537736 diff --git a/model-00013-of-00044.safetensors b/model-00013-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b86811a09706220b8e687f51c7ac79f16ca97ee --- /dev/null +++ b/model-00013-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9a8978d2163ff97a8a36356ec20e2acaa6eb52065ca112e2b0bc798bd32212 +size 4806722832 diff --git a/model-00014-of-00044.safetensors b/model-00014-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fdbfb0175fc48725fd8d8f2df7cf5bfdbb60c71a --- /dev/null +++ b/model-00014-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba582bf6b7d09a4f5c6cd8d52a830710530e2b46c519e056ac33b30c187fdad +size 4630537736 diff --git a/model-00015-of-00044.safetensors b/model-00015-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e533a4669b418aadc4c254d3892d1194eccf2d22 --- /dev/null +++ b/model-00015-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61e6e90776c6486487fd367eb548779a7c7dff9d0c5dc451929042471fc5af3 +size 4806722832 diff --git a/model-00016-of-00044.safetensors b/model-00016-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e39f1ec6ad1450d0e5de2d84aa2b07cecf366f16 --- /dev/null +++ b/model-00016-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f6e713c18ef2aeb93450e906cea3f524b110f6d65cdbf58dbf4976099b6e45 +size 4630537736 diff --git a/model-00017-of-00044.safetensors b/model-00017-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ae58cd73addeee8c42b2fedc419094c3e0c581b --- /dev/null +++ b/model-00017-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6abb890c55f8c06fbe11ed0c5c5dba181996a9f06c786cae75f1194fdf6f21b4 +size 4806722832 diff --git a/model-00018-of-00044.safetensors b/model-00018-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd1546f913e62993797a617ac6d958ade33c928e --- /dev/null +++ b/model-00018-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff61cc813c45a48ace260dc504d069cd95b20b6ebe8004e4118e991ff172d189 +size 4630537736 diff --git a/model-00019-of-00044.safetensors b/model-00019-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca33093d65c49db2b3dbad2264617f2a2e6739c1 --- /dev/null +++ b/model-00019-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396c21c80bd10294b40010d548dd2889e151052778a8a1950ba30f4eb66180e9 +size 4806722832 diff --git a/model-00020-of-00044.safetensors b/model-00020-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cae28c4bfc56fc2292dcfc81c792896e18c436d --- /dev/null +++ b/model-00020-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c5403977f5f5f0f2d591b3aeb9da5d3ecf3ec96541de75fabc093598fcaf25 +size 4630537736 diff --git a/model-00021-of-00044.safetensors b/model-00021-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cea9036bc485787689edd6af09609421e1c338a4 --- /dev/null +++ b/model-00021-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729dbf98523906b7a2092fe6c0b8adbbb3ccd5f25be855c7a4b65b5b656f6b4e +size 4806722832 diff --git a/model-00022-of-00044.safetensors b/model-00022-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14492f53c345ed4d83f2eaaf4035f6281c3d3f5e --- /dev/null +++ b/model-00022-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca0c87180a84ea36e61f9e93028972b1cb830b5a836e702c0af1bd564628b1b8 +size 4630537736 diff --git a/model-00023-of-00044.safetensors b/model-00023-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..593dfc0d935d74809fd0cf5e92a468574037aa76 --- /dev/null +++ b/model-00023-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d458b1fee0f4402f73e130fca142e69b995331e4b39cec75421bc588945302 +size 4806722832 diff --git a/model-00024-of-00044.safetensors b/model-00024-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6abe704f95b2870dcd0d1261295487324b122e5a --- /dev/null +++ b/model-00024-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc21917e5848aeb5b2d1c1acf27a3ebadecdbbc86f782dc5e15ef22b86eef95 +size 4630537736 diff --git a/model-00025-of-00044.safetensors b/model-00025-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a6784219b89b810a0174bc21a1af8d9e2c6c50c --- /dev/null +++ b/model-00025-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:955418426b0b47c15a2e115eb0f006b26cf7b735dba9c0479d490c59827e62ca +size 4806722832 diff --git a/model-00026-of-00044.safetensors b/model-00026-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f3c00adde4a337d3b62d2887bdb7c230c037f3a3 --- /dev/null +++ b/model-00026-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df23ca35ee3049caed3acb90b191793eef2a24b80c23b36e27b0d4315e5baf1 +size 4630537736 diff --git a/model-00027-of-00044.safetensors b/model-00027-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6a5c077b79957adeda4ad1d98ec485c18c0675c --- /dev/null +++ b/model-00027-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0f473ab5803f8ee66d42f29d9cefc08e6e6cbb50d851e0c4a7b06c343f2dd8 +size 4806722832 diff --git a/model-00028-of-00044.safetensors b/model-00028-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78901e2874f6479012d5d3d984c11c6a66d23dda --- /dev/null +++ b/model-00028-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff224ab5f7c54f93c9e4553687a7ccf7bdce5bbc39db430b6f1f4ae23ca8b7a8 +size 4630537736 diff --git a/model-00029-of-00044.safetensors b/model-00029-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..931454829dda089923b2197f3aa1ad3668afaf45 --- /dev/null +++ b/model-00029-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0657ca15f016fba580184a3e9ef78f42af036c9448a67d2a999df9a8d81c479f +size 4806722832 diff --git a/model-00030-of-00044.safetensors b/model-00030-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aef2e0c960855a42c5b93904bcfac3cdc312d84a --- /dev/null +++ b/model-00030-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cedbbf16f74e102594d25b9ecc23d38bac97ea2c9b16977e218d44be53d86cd +size 4630537736 diff --git a/model-00031-of-00044.safetensors b/model-00031-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bfac441b80a84c4acf3edffd075d557880b9d94 --- /dev/null +++ b/model-00031-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f740ac6fae4ce6b940f0ffa5da460bd7634159a7911f81523a462411e1c48e0a +size 4806722832 diff --git a/model-00032-of-00044.safetensors b/model-00032-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57d10d6899be2fb6df5614053c13994e3ade6913 --- /dev/null +++ b/model-00032-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e60e04926ebd67693a9a35289a1b80926d2b4f462daa0148f3a805a093cb441 +size 4630537736 diff --git a/model-00033-of-00044.safetensors b/model-00033-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d55bca49d99a5c96c99664d393ff7a97be7dbd3 --- /dev/null +++ b/model-00033-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4980b44ad90b5f318b8ea248dce2c9b9e6304394b71e28debb8f7f000ee4f99d +size 4806722832 diff --git a/model-00034-of-00044.safetensors b/model-00034-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b0245d504fafb3861c1453e146f37afd66ec063 --- /dev/null +++ b/model-00034-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:927564a734b765eef03b70b3637d07897b0863e1728864e94f0bcc1e479dbb93 +size 4630537736 diff --git a/model-00035-of-00044.safetensors b/model-00035-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e615fda4516299dfd8d7f353aa01d65ff18244f --- /dev/null +++ b/model-00035-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de495c93ab80c35c84e14521ccf292c3b6cc14758175a0b40fe42fa092f831f +size 4806722832 diff --git a/model-00036-of-00044.safetensors b/model-00036-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..574d2f53ebd99b027f80c0af303168ecfe2e4391 --- /dev/null +++ b/model-00036-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bdf66905d4d0f9e9aa71ed0d8430db2a8a5fe9eea6d59c41e598f11388b1462 +size 4630537736 diff --git a/model-00037-of-00044.safetensors b/model-00037-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5b5e8283e78b977da9d470b0b6f1569324ec58a --- /dev/null +++ b/model-00037-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae022f4e91db2a5b13cb21ec3771e1304e7ce2124037f889e84e65057476481 +size 4806722832 diff --git a/model-00038-of-00044.safetensors b/model-00038-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad92ee49c4f9dd74af1cdf833d5136074bbc87e3 --- /dev/null +++ b/model-00038-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90610f2c38a4f2741f243db87c01c5cef1e0f72478826f311a1068971a0652ce +size 4630537736 diff --git a/model-00039-of-00044.safetensors b/model-00039-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f01b5a155fc16aac767aab92547b35aa714b006 --- /dev/null +++ b/model-00039-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa0291b13e44e35cfee7b597d3e3f1b246a6b41b3f12119819fafaf55871a20a +size 4806722832 diff --git a/model-00040-of-00044.safetensors b/model-00040-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbe45c1b778a130a27d22fce0c52faf0ab9d813f --- /dev/null +++ b/model-00040-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f5906fbbdbd687bc91b0017e5c1d992d57b90013e8e0aff764fff9c7700839 +size 4630537736 diff --git a/model-00041-of-00044.safetensors b/model-00041-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86c24937ed907ce6f65a7059f53a7e6924d6e4ba --- /dev/null +++ b/model-00041-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92317d8e248964525aad1fee3305b4a97080fd1600aab9d565fce7ca54041ceb +size 4806722832 diff --git a/model-00042-of-00044.safetensors b/model-00042-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8dd93a3e20e6aae9cbf016cecb4efe19f3897fe --- /dev/null +++ b/model-00042-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5d085366c5a06e1f937954ff6f0b25244962bbf4c76a6042cc4f9852215211 +size 4630537736 diff --git a/model-00043-of-00044.safetensors b/model-00043-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dbd21a04d41e7b4f06abfaebcfbb800c5ae2faba --- /dev/null +++ b/model-00043-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6dd842cd9e497490f32c1bd22b03a5a006b16e1952313c2c81ed3adda0893a +size 4806722832 diff --git a/model-00044-of-00044.safetensors b/model-00044-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ff040c45c8c6a17328ad96d46090aaed38b0704 --- /dev/null +++ b/model-00044-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97bfd1017d47f9aa31bad7e02b3c27adbb631a07c3af8eef2ac5471c5afacf8 +size 3145778200 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..160882a4d7de7c811394100600fe051a1b15cfa2 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,521 @@ +{ + "metadata": { + "total_size": 207619645440 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00044.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.10.input_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.11.input_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.13.input_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.14.input_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.15.input_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.16.input_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.17.input_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.18.input_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.19.input_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.20.input_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.21.input_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.22.input_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.23.input_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.24.input_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.25.input_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.26.input_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.27.input_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.28.input_layernorm.weight": "model-00021-of-00044.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.29.input_layernorm.weight": "model-00021-of-00044.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.30.input_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.31.input_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.32.input_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.33.input_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.34.input_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.35.input_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.36.input_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.37.input_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.38.input_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.39.input_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.40.input_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.41.input_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.42.input_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.43.input_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.44.input_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.45.input_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.46.input_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.47.input_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.48.input_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.49.input_layernorm.weight": "model-00035-of-00044.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.50.input_layernorm.weight": "model-00035-of-00044.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.51.input_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.52.input_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.53.input_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.54.input_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.55.input_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.56.input_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.57.input_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.58.input_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.59.input_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.6.input_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.60.input_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.61.input_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.62.input_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.63.input_layernorm.weight": "model-00044-of-00044.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00044.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.8.input_layernorm.weight": "model-00007-of-00044.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.9.input_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", + "model.norm.weight": "model-00044-of-00044.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..cf33f2e5e3a66711d05c07c8047dcdb59005494e --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|END_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5cb5ee2f541e32fa23cd73f81a8961a7847fb1c2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6445161e1d288233dd401927b66ba44b2c987ae27150fbf2f6b54237833d2ce9 +size 12777504 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a8c68140c43bad064fef69e45f95f27614c05b65 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,316 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255000": { + "content": "<|START_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255001": { + "content": "<|END_OF_TURN_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "255002": { + "content": "<|YES_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255003": { + "content": "<|NO_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255004": { + "content": "<|GOOD_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255005": { + "content": "<|BAD_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255006": { + "content": "<|USER_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255007": { + "content": "<|CHATBOT_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255008": { + "content": "<|SYSTEM_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255009": { + "content": "<|USER_0_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255010": { + "content": "<|USER_1_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255011": { + "content": "<|USER_2_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255012": { + "content": "<|USER_3_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255013": { + "content": "<|USER_4_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255014": { + "content": "<|USER_5_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255015": { + "content": "<|USER_6_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255016": { + "content": "<|USER_7_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255017": { + "content": "<|USER_8_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255018": { + "content": "<|USER_9_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255019": { + "content": "<|EXTRA_0_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255020": { + "content": "<|EXTRA_1_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255021": { + "content": "<|EXTRA_2_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255022": { + "content": "<|EXTRA_3_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255023": { + "content": "<|EXTRA_4_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255024": { + "content": "<|EXTRA_5_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255025": { + "content": "<|EXTRA_6_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255026": { + "content": "<|EXTRA_7_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255027": { + "content": "<|EXTRA_8_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255028": { + "content": "<|EXTRA_9_TOKEN|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "<|END_OF_TURN_TOKEN|>", + "legacy": true, + "merges_file": null, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "CohereTokenizer", + "unk_token": null, + "use_default_system_prompt": false, + "vocab_file": null +}