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..bd0d9a155107851a8db739627212cc5f38129c2e --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "_name_or_path": "Sao10K/Llama-3.3-70B-Vulpecula-r1", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "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": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.49.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..604054b78e8c9a381fcc06aef5639fc1c13e4bc5 --- /dev/null +++ b/model-00001-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73f9d97400eb59d54f8c227bc9159e8b63886bdaa99715211014d8fbb19bd275 +size 4202725616 diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47fa5f05d2f23647c8c3b2b00f0bbf82300efdcb --- /dev/null +++ b/model-00002-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278fecac681b3b1b37944ea1e0d12422aa2d615c926203b232af83a1809a03bf +size 4202692744 diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8933072f373c335103ed0caac8942c91127d263f --- /dev/null +++ b/model-00003-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a6cb0a7c9e4f9c4b0f972f37f5f4218d51b41edb3ffa72e559feea77a03389 +size 4362142872 diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e731f495bc6435b065b8fc59b56a5aba8ac50736 --- /dev/null +++ b/model-00004-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f0b1740b63e6084bf23ad8a857a80840f52fa07334efa98fae51e99f064d8f +size 4362175768 diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dda24a9716f468db1676a9d922b1311b65dd2770 --- /dev/null +++ b/model-00005-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65667b6dd24a14140dad19c4cbfbafed82159574f32eb2bfa607005bbd598276 +size 4966156008 diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e1c16aff07810ca42802c8682f83596343d089e --- /dev/null +++ b/model-00006-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbac993026afa7600801ce1dde91ddbfc47ce321f20a0b8d93f701007102ecdb +size 4362142888 diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eaf1f5a8d74b727979064b6f6e5674d80097a09c --- /dev/null +++ b/model-00007-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91568a3f66b75468e3b10d8dbfdfb148701fbc4ed65be1103f0d90d82265159b +size 4362175776 diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1a3f6e7a6d782459cd58ac665b186a571922ed7 --- /dev/null +++ b/model-00008-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa25e40cc9bd5b6eb128e480e5b69a5e52fef0560e2d389941e2445624a82d1 +size 4966156008 diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ea413b10b0b126fab64b3f8a1160364d36d7366 --- /dev/null +++ b/model-00009-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f728a569283ec802895f88522f8f74ec2b46d43bbdcce298439da3a1dd21a3 +size 4362142888 diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1e381a6089d66ec301cc050ff36679a1a17aefc --- /dev/null +++ b/model-00010-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651caebca29dfd2253dad6cb869152c1ee009a6b615c80bb1b0ec79f3a633a11 +size 4362175776 diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4273d7f2c76a7686cbaedf8eec75fc8b44dccf99 --- /dev/null +++ b/model-00011-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb247a8cf552f645553e0270261c4d9f2b53d6b3890f32c17d46db507b001af1 +size 4966156000 diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7821a23cfe4f66e0cadc42946ec8f0e43fd6ce0e --- /dev/null +++ b/model-00012-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a8c9fd72f28181f57364602c44cbc7a494a94976edb0f812ffdcd5ec6b03e4 +size 4362142880 diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ae08b3d1d305fb0918c449bdce702c03940d4d9 --- /dev/null +++ b/model-00013-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cb4b7dfae91aa2f3a35f1d2d72baf6470627a25228956c00e551f0eb4d462d7 +size 4362175776 diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66fe8295518fce5d6cac31c1b645172fefbc0ae2 --- /dev/null +++ b/model-00014-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d2880607957d99700e4199171e4a8d49124d01c3ab412d2c9325799300c129e +size 4966156008 diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..985c695cb1da4f1a5fee669ddbff23deaf05ace1 --- /dev/null +++ b/model-00015-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4154756c0c6f82ce428f6c8a366a47f3aa62178bd64b3b8b491a37a93a72555f +size 4362142888 diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94895b6a77c0f466b2a55ac2357551ce8191169d --- /dev/null +++ b/model-00016-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d069485fc7058b78f29f076bd71d214bad50d1928d249515356ec74496fea2a +size 4362175776 diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f636a8ec638ddec8f1a4f72b68fd075d608df7c --- /dev/null +++ b/model-00017-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e4d008ef0d75afbed0797a610f5287f2ea2401b688595cf07d410f57f30c5d1 +size 4966156008 diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0885d260b6fbf0f8eb23ff39f1a7574d697a93cf --- /dev/null +++ b/model-00018-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145129f0f619526b160d1c1e5959f3793f9a1bc16522ffb42df4a0cb29f227a7 +size 4362142888 diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0db1539a34dfd5414f01941c9c03c8cca460c18 --- /dev/null +++ b/model-00019-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1061d78dbb5fb18a98ad79f6a0c14d0145e02ea9958de0be64da7128a2daf447 +size 4362175776 diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..202cdc623e7b2ef4b058a3ced5d1de2f374926ed --- /dev/null +++ b/model-00020-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a26d0177c230e4b375425ba65d4a9b76f6d186dbd9d49bdb014e6102175266 +size 4966155992 diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6ebdc3544da29fdce93e8e878a4767e0c20aebd --- /dev/null +++ b/model-00021-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285bef6deef4071f57b2e83ec8c67698de0b58d31809cdb4c557d2f1409a4f81 +size 4362142888 diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..44e41466ef808eba42400e99dca0dd538cdb89d7 --- /dev/null +++ b/model-00022-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ada0b7d5a0ab25476a450c066a189860ef7abdf4fe0d095019f1711356c8894 +size 4362175776 diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..010cfe96d14ed7fb2efb951b3c5c6c3e2884e962 --- /dev/null +++ b/model-00023-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17666d2283927e721d70395bc5889314b02adc735e2eb37c0bfe4ad2bce1a58 +size 4966156008 diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32bc3e6fa73d909158d721d832ff2e55dd43b144 --- /dev/null +++ b/model-00024-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ec5f66284d1dd89ea6546c8ab25646565817d8655e5e4c392a22c5698cf825d +size 4362142888 diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b093302f29975a22b48cf6265b869bdc40d627b9 --- /dev/null +++ b/model-00025-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6387b90bcde8a4b2bdb60c7145e7c564164c8e2046a53135c42ad32b57818f6 +size 4362175776 diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..730406c9ec0a23aa17398cc4ccacf2bf872f85a8 --- /dev/null +++ b/model-00026-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e0b5c9489948fa76a8e11b5e34df3c8f6bc55b9761d8e80ad49e7f46b52ef7 +size 4966156008 diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d4230b6c75255ea51aca62f075c27a7edfb26c3 --- /dev/null +++ b/model-00027-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d7aa5a3a95d3839602203b1769d1218c5840a696be15c66d8b6f33c80bb278 +size 4362142888 diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96b36c9ed1b7db63443e338e37a070985847b570 --- /dev/null +++ b/model-00028-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b077d871ee079d28148c3b726294fb8fea84ce44c482b3ef765a66d2cf1dd7b +size 4362175768 diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ef9ae39b82b22d3906b5c0ed6efb7f954e8a17d --- /dev/null +++ b/model-00029-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29ef4733019d16095a0d3af467b685c2a9d65650bfe1db344918dc128acadff +size 4966156000 diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..037436fce64b2bad822b778428046807ea515933 --- /dev/null +++ b/model-00030-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daaa4a93799a173e5559fbac11b59d130bf191131fff697e49b34b2d49ab1304 +size 4362142888 diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fdbd18c48e350753b26f5748c8b902f99bd9a08 --- /dev/null +++ b/model-00031-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f016e4d6e306cc3e037ab2ea287cc2e83016442f25db0930ead4fbcd985cb68f +size 4664165896 diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..849728da56d1d720ca7db7d23f3005356f057601 --- /dev/null +++ b/model-00032-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2e035aff865fcd46f3da82af0e4c8097f9ac31ce6403180fb734e6a08470fee +size 4664165880 diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2ad82adbab8d50cecfd1b4b4dca6071bb97682a --- /dev/null +++ b/model-00033-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0cfeea50bb811d70317a1239e0e13d4bcb4b0844b88dc3ea7fa4cbb3ba4dce +size 4362142888 diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0992003f0be0419d93bd7a855fc258bb6a9e04c4 --- /dev/null +++ b/model-00034-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eaccd9982d3ace47b17d97babbe0d6b5b746d406750177ccfdc808f226b4f02 +size 4362175776 diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88c03fab67ad146183d946d7e13caa598a7bed3c --- /dev/null +++ b/model-00035-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455b7f67ce011f519a8ae60c76748d198747c4865c774c37ad931af62a116b4c +size 4966156008 diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6eaba1676878311170f8a04025c0c7d940490d86 --- /dev/null +++ b/model-00036-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6683488cca19b7949300cded8d018551d74ac37df3613fcd54118440ef88cd43 +size 4362142880 diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af83683b02f3e32be75d38d8489bcfa449a56ea5 --- /dev/null +++ b/model-00037-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd11a5800dabd5eaab77d5a52bc96b0eb4cc2449f0ac53b7c4b0228e16e9ba7e +size 4362175768 diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f620f148c6f9f385270a6672e2ccff31980173b3 --- /dev/null +++ b/model-00038-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3017753f5e2e55d9cbade08015969564582df260607189355832e238372515e7 +size 4966156008 diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91cfd9a7dbf4e349ba941ee68e26301576b1da0d --- /dev/null +++ b/model-00039-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3c56bfd4191535f1532e9d6e271be206b10d5e7a0a7ffcfe068e117a6e05695 +size 4362142888 diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb2bd58210088cba00c57993e4b7da7da8708d66 --- /dev/null +++ b/model-00040-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e5b23ebcaff449d48f0daacf4e3d2c8ffe5bf5a81e97f5166b8fd054df2eaf +size 4362175776 diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d1b5f9d6eca749f7dd5b5ee5b42ef8a2bc852fa --- /dev/null +++ b/model-00041-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da243899403f21ddb72903592de7f2e416a951635fe0b7f8611f4b1f2abf933 +size 4966156008 diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3ab84821104e66396f5f368c8bf9ad2dba52019b --- /dev/null +++ b/model-00042-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c46f54af97a9c67687f8a09f440dbf1c18f5b470cfae71a6e287ba54740a336 +size 4362142888 diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5e13bb8ce411e1767739e558d21bb8cfcad7841 --- /dev/null +++ b/model-00043-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feab4d27f40f7b39724fcc679c475a83b8df1052f955232663b1a598aaa68859 +size 4362175776 diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9551562b46f4aa2e4326add93bffdb513847ff5a --- /dev/null +++ b/model-00044-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5616be4588517ea64afe6e61449960fd1cf11b0a364da44b576590228b93e1ea +size 4966156000 diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f2358024ae9a3f08e18fd3568c3b48abca2742c --- /dev/null +++ b/model-00045-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c177499ea41e69c5f7654109171a4d4218cebe9a86efd7630977b081ee270c5 +size 4362142880 diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa0c00d5d76dae94157f12ddd937743a37515775 --- /dev/null +++ b/model-00046-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31295d8794996257fe4433844478ddf65b774af7a0d349b4d5142c6bf4c612ff +size 4362175776 diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3867ea134406a5186f94b740c5194449d3b2f5f4 --- /dev/null +++ b/model-00047-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c82b513fcb17feab28ddec406f0d9d949bce67d1f502b892b3afd0356a3154 +size 4966156008 diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1ac3f5a778276f1f493905d75a156831c6a898c --- /dev/null +++ b/model-00048-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b9b45832777ddc10ad82f3208314848d4c8a9bc6196b621ec76a7e1bc52e601 +size 4362142888 diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d5aec211c3f11fec44223db2bfa42a7a58f82b7 --- /dev/null +++ b/model-00049-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39fb71a2c6c6b6c177f099722c9345841043a0f41997f7019c9cf75f4d7e3c0 +size 4362175776 diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2994058df7f1a05df65b70404b4d0f86bc5230b --- /dev/null +++ b/model-00050-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180da50413bac0558098fbfe3b8810b0698a027f70270ae01036e581c7e102c4 +size 4966156008 diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b1095a7a051cbafcfcca15c2e79548d7c6e5e84 --- /dev/null +++ b/model-00051-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd25c985d3feef535daee398f3cc5fa6e45f14829b36e507032a055d24199e8b +size 4362142888 diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f935df008cd7b90ff380cced499c62cb748c37ad --- /dev/null +++ b/model-00052-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d53cde2a806e42ea8ae051720f2763a6fae357b48090c2ba3e44625bbd44d6 +size 4362175776 diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e85bf21cfdec314a0527e92ce1cb42d6d459c00c --- /dev/null +++ b/model-00053-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78caa55ac9ff4c72db6df5b28d1736b9deb897a3a6640c0739fe040683731426 +size 4966155992 diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7398d36931dcc68c8ec9002618e5f6a7909c9df --- /dev/null +++ b/model-00054-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15aa711e481440d7766eb784c70294679a7beab99950d6640b41467e72fcbd26 +size 4362142888 diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13de7ac7285096d09b18626a5afdf340fef6ab49 --- /dev/null +++ b/model-00055-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b05933622d31a0b785b69dd8153a7d7edf478a713fdb1e0782ea8fadc0a35fe +size 4362175776 diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab407e6a215a288bfeb27279ffd58a6efa263cad --- /dev/null +++ b/model-00056-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685a75b673841b69427d04bf966a043ce672e724737e3cc4586ae0287ca703f5 +size 4966156008 diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d653b7e787b1799f275de9c14a16565e26d8d5df --- /dev/null +++ b/model-00057-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9491d69a4e3b9e740128b4436b8bbf25e6db247a338aec21693f477a269f743e +size 4362142888 diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ebd8139213b6697c0c210d5846e2692f6a975ba --- /dev/null +++ b/model-00058-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568434a5079027bc104008d8ea2d8977619861c26ed4bb84a3e96a22ecc76272 +size 4362175776 diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a49199e64b9cdea7de28f9230fa637dc48f35c18 --- /dev/null +++ b/model-00059-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be1cdcb88ba6d79f45a7bf2e0c05616a152d90d677f81f21f83651ce4e40d63 +size 4966156008 diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be9f24d13bae29a52ac9ba014b42cb2c4abbdf6b --- /dev/null +++ b/model-00060-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd7093ef224e9b1f0a6b28bd466a996351db080ca876c2f59d835071aa8d903 +size 4362142888 diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cfe95374a4ad5bce4aa9cc574f25cc4d89b6382 --- /dev/null +++ b/model-00061-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f572fc96ae10baf74f07e6f7873a183f56dfa5380a1334b0c2b2b56254d07ee3 +size 4362175768 diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e7c5f0db6be6ca6cb81367d73ed8e974c0da286 --- /dev/null +++ b/model-00062-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d751d86654196a6ec9e11d58d928e22a285bb83cbc3e6d2d34365e42aaa9166 +size 4966155968 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..0856922b37f249a92f164a3d8e1903acc6a093b9 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 141107412992 + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00062.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00062.safetensors", + "model.embed_tokens.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00062.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00062.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00062.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00062.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.14.input_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.input_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.16.input_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00062.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.17.input_layernorm.weight": "model-00009-of-00062.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.18.input_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.input_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.2.input_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00062.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.20.input_layernorm.weight": "model-00012-of-00062.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.21.input_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.input_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.23.input_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00062.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.24.input_layernorm.weight": "model-00015-of-00062.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.25.input_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.input_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.27.input_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00062.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.28.input_layernorm.weight": "model-00018-of-00062.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.29.input_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.input_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.30.input_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.31.input_layernorm.weight": "model-00021-of-00062.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.32.input_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.input_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.34.input_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.35.input_layernorm.weight": "model-00024-of-00062.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.36.input_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.input_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.38.input_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.39.input_layernorm.weight": "model-00027-of-00062.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.4.input_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.input_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.41.input_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.42.input_layernorm.weight": "model-00030-of-00062.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.43.input_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.44.input_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.45.input_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.46.input_layernorm.weight": "model-00033-of-00062.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.47.input_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.input_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.49.input_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.5.input_layernorm.weight": "model-00036-of-00062.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.50.input_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.input_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.52.input_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.53.input_layernorm.weight": "model-00039-of-00062.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.54.input_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.input_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.56.input_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00042-of-00062.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.57.input_layernorm.weight": "model-00042-of-00062.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.58.input_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.input_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.6.input_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00045-of-00062.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.60.input_layernorm.weight": "model-00045-of-00062.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.61.input_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.input_layernorm.weight": "model-00047-of-00062.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.63.input_layernorm.weight": "model-00047-of-00062.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00048-of-00062.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.64.input_layernorm.weight": "model-00048-of-00062.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.65.input_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.input_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.67.input_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.68.input_layernorm.weight": "model-00051-of-00062.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.69.input_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.input_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.70.input_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.71.input_layernorm.weight": "model-00054-of-00062.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.input_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.input_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.74.input_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00057-of-00062.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.75.input_layernorm.weight": "model-00057-of-00062.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.input_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.input_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.78.input_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.79.input_layernorm.weight": "model-00060-of-00062.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.8.input_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.input_layernorm.weight": "model-00062-of-00062.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00062-of-00062.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00062-of-00062.safetensors", + "model.norm.weight": "model-00062-of-00062.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "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 + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ab986c51d19ae80150cf45c0291463638a03ab27 --- /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": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "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": "<|eom_id|>", + "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": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "tokenizer_class": "PreTrainedTokenizerFast" +}