diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d416aabd6fb468891594bddabb40d2f3933fbe90 --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "_name_or_path": "meta-llama/Llama-3.1-70B-Instruct", + "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": "float32", + "transformers_version": "4.46.3", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..aba45c8e2bd7d66ff3a5e250c9e9233e137a752c --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.3" +} diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9db979ed8975b9463d1d86767977fcddbde9d9a1 --- /dev/null +++ b/model-00001-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995918030d8ff5acbd5cdde18276596d0afaf5c68369bcab7aa1f44fb65be2c2 +size 4806672984 diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce8a1d4d62ef91f0f0a255afba17f02662966bde --- /dev/null +++ b/model-00002-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9da25bd05ffcd9f66a161233f75b85329491d34458ef9c3473c2991fcf4968 +size 4362142864 diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4352ff334418dfce7b1bcb37c93fec3e7527f8c1 --- /dev/null +++ b/model-00003-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98abb2a303ea166336690957ad5dcd0bcfbd28d322834c67cef15ee2167ac32a +size 4362142864 diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58f7ba7a2beeb810d338f9edaaa2bb4abd34a75a --- /dev/null +++ b/model-00004-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119c68bd67289c53f70fedda23195fd10792f23e2983237020de9f1907638206 +size 4966188864 diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b170f12eb202b57f89421038b62ce87f0d5a406 --- /dev/null +++ b/model-00005-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ae41491e31f3039bba9544b1ae83a6927b39bc4608bbd7a304d96fb9e12d8d4 +size 4362142864 diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5938a2ab6ce40654fd20928ac7d0f4e1d502c864 --- /dev/null +++ b/model-00006-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62f91122a6351b638cf8062d91a9d65f88a7c1ab6ef4a7589e8ab1fc4631796 +size 4362142864 diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba33718f84238e2e6b8bad5820ce8e72a3f227a6 --- /dev/null +++ b/model-00007-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0af954666c818986f8c467de08d4cf62e5bd9b9b85b57e04288e40208d7c573 +size 4966188864 diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b753a6b0f07342e70743dc18fd9a2fe2b9a1b7f --- /dev/null +++ b/model-00008-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5de6f61bd5e105a9247caf036b566a72a7f1e7de7c286efb84d0e52cf536fc7 +size 4362142864 diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6558d3eb47c85c061f6efa81b9165ff764ea107a --- /dev/null +++ b/model-00009-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105098a40517be8a19f2690c1803eeb7558d29a26636170641b164610ee84d94 +size 4362142880 diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4849eb848893cebe26c3890cc862da4f05f68af3 --- /dev/null +++ b/model-00010-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a7b7f70950a501c61fbb3d707140ebc11a498f60232757ef351792366b05b5 +size 4966188880 diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f41c135a636c9518011310a53f29c55eb4cfe32c --- /dev/null +++ b/model-00011-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6faf10394af7a5fa1b06f14285bda7772ccbcabd9a2913ba7c9187dccfdeae29 +size 4362142872 diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f752ef084b92a36c5079a5d6599f8c2fa6503971 --- /dev/null +++ b/model-00012-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5332ca9241f2be64e8cf02d066ae0a39328d9b0ed9e0ccb4d8a81f2a9e9e75a0 +size 4362142872 diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..988e951affb677f80675dc0993b32903c3025350 --- /dev/null +++ b/model-00013-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6900e7eb8acd45360efca8536f21835b4098e79a16eef01ed90f3aa2eb569c0 +size 4966188880 diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ae3f3c7c487ca07caf8479b46994b8f1fd16d43 --- /dev/null +++ b/model-00014-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523b8a098bc5d92d33c77404813b22fcae38dc4c3cc694487643b06437425510 +size 4362142872 diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28b3a633e1a90058ac0ce01ec9a15e2528719ee0 --- /dev/null +++ b/model-00015-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb27241aa3ac8a1271096064f37fa872777b68e39be30e1f3dfdecad63564c20 +size 4362142872 diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd926c9b36f9c2ba348d7d1b138b71a73a5e76b1 --- /dev/null +++ b/model-00016-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b1f61de35e62ee4b38ab2032fc0c950ebb60fa1d52a96ecd63fad0940fd5ee +size 4966188880 diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..311dab5bb7cd1af6ce940534c2dccf2241ea87c2 --- /dev/null +++ b/model-00017-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abadee78a10b8ff56c0c7c4843c8f4d6662a108e2ebbd7bd2b9e3056acec5962 +size 4362142872 diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40fe54a26be83addebbadf04946028253f94c2ab --- /dev/null +++ b/model-00018-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cbc431d69aa3557d5ae26d2910f02ecb0ae59449fafb891f6a4cf7e14418fd +size 4362142872 diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9974b4839b2294941a26f0a19e941f86369df185 --- /dev/null +++ b/model-00019-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:090d0ece08a734122f48769e1e6b57a2ff65f181decca05f1b6c47b94d8f702d +size 4966188880 diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5fc6f569ef5bf7a10d24127e1f8d4f63461069d --- /dev/null +++ b/model-00020-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68952eb6da619cff07e6c2a0ea2cfb9e0fe6a475a623c679cdfe20fc5c1651d3 +size 4362142872 diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1cb5e35120325d1edf7959f66c24411822d840f4 --- /dev/null +++ b/model-00021-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3bcf49cc7b5c3840c7108cc0f2ec433cd168b2ebc95d444f8d7d38efc817dc8 +size 4362142872 diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48037217c279f03a634fe83048fffa2fe658ba97 --- /dev/null +++ b/model-00022-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1fdd2d31e643b1484eb8d32dc85a68c1460c2caf2ed47c94ff190df2f0f212 +size 4966188880 diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d254f47223219729af7d9d776c62858f712aaee --- /dev/null +++ b/model-00023-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b006c71886fa988b121d6d929721b13db9ff08e2f91f90989633d4dae8b0e7 +size 4362142872 diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01cf32d92914a2d612f352a0dfe2827470f7e7f9 --- /dev/null +++ b/model-00024-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206b24d72de979d306c4c2d93bdb509a6360f16306617b445552bfe01c3d4dc6 +size 4362142872 diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..784d07773975f62c3e1b8e44eec57fb483f0096a --- /dev/null +++ b/model-00025-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f561af8b9c94202c3b19f44b50c49b0b436ccb7a90e3f5feff336422734f0a +size 4966188880 diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea11d851bb486fe47a6febcca2494cdfcf5031a2 --- /dev/null +++ b/model-00026-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4977dd0840419f59866da90d0d750d0d7477765d31b22f49608775e5f50c99a2 +size 4362142872 diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90f7f67180e99a15d067210bc7825330f8778c69 --- /dev/null +++ b/model-00027-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba565b707250ddcf259d1470bb8f3e640fa2d6bbb25249b85f5adbc6a9ae04db +size 4362142872 diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30528c967b42f62fc18e9776e63564b3bff8500d --- /dev/null +++ b/model-00028-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f34ce2f014323aae237610e3c40d737e10a291f96959e4a4447a8d12f3f2d1 +size 4966188880 diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc15144d99894721e28ace5d9ea2b0cfd3c2be77 --- /dev/null +++ b/model-00029-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bc2ba40596e7a0b076b5ef8a111271367ac10ba18b17b5b66e5471475ce5d2 +size 4362142872 diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b3f93112ae644eab529c42d95ee6031df2c02d1d --- /dev/null +++ b/model-00030-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8488e31c285781984e5aafe41a22f27348e150405f7547fca2c787e08367914 +size 4362142872 diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2657710582ab5fa89e9261ce5cf5670e6a025047 --- /dev/null +++ b/model-00031-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662f0cec6350aeb946d3e9a6daa88c6f242957635e8b9d1ac3c6de277a9047e0 +size 4966188880 diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..907bbdde07e2490c9f4369b6251c25375d2c4dfe --- /dev/null +++ b/model-00032-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb6792dbd8926f36cf212f49fb084e33f55028f1004aa681816ae819ddcbb76 +size 4362142872 diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a699ef857fa4c92a38151d822c78d84829d2c3d --- /dev/null +++ b/model-00033-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:218e0baeadad523f14998924284904f10f345ff59fddfe3dbfb3b4b798969863 +size 4362142872 diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee1d2115121b26fcf7f80a01494d9faff10431b7 --- /dev/null +++ b/model-00034-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ea946d7e740dfee1fc8df00bbbdf258af73f58ad718d26b40904b8918bfb07 +size 4966188880 diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf8786a2fdf3102cd504cd90c5eb4e66ab99e7c6 --- /dev/null +++ b/model-00035-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ca7069c950b14633a9da8ca5f5c6dbb3c67707926448fe8916487d37e5ab52 +size 4362142872 diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1e37c73300475303023dc44630491b10b4b58fd --- /dev/null +++ b/model-00036-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e0fa4a6af0e6ad2f255da2f0f067841a15513e434b5db93abc3c20aa3334115 +size 4362142872 diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69b892d351a034c1c44c010bb505eb91019a7c0f --- /dev/null +++ b/model-00037-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ac564d204258ab9694c3ca708eea5fdb21e8c4b9e7f7cc6889c84834aa4329 +size 4966188880 diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7511f027e1d4f7194a98cbd4eb491dd8001720bd --- /dev/null +++ b/model-00038-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5748206318a01b01487712e5628597aaa4be642638a651df703c68b9e98bb7bc +size 4362142872 diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a0720d0e7a3ecc25269710312633faf18fd0d68 --- /dev/null +++ b/model-00039-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3388a4fcc4403325368d833fa282728249c211ac9724437be24a92b1be6b0bf +size 4362142872 diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e833eceab877b5e512539fbf3fc15f26d11df7f7 --- /dev/null +++ b/model-00040-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b9d2c5812a727c989b8ada4d7e75380c3de2e15d55f27823b8ed630bd583d5 +size 4966188880 diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66f600d16a6b6dea1d5fc7a9191e0ef0c59b9c62 --- /dev/null +++ b/model-00041-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85dacb7b96033d84ba33862ec933ce6e421477ec15915761cfd539304c5e1aed +size 4362142872 diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b7246eb8a30ad86e8c20a350c1f2720c8f9af51 --- /dev/null +++ b/model-00042-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab99e9c9f66976f7495a3d3a68705b0d5f8a4cf041664c7b46c92fe9c8c345ed +size 4362142872 diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01a432ee124d3e7b8ddd332a1a59041d998b508c --- /dev/null +++ b/model-00043-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe46cb9081d00335e7aa427b9121919c00bc9d835ccb535b32b8a47115c713d1 +size 4966188880 diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05ae40eab6255f752ea3dac05e359061dfb47a7f --- /dev/null +++ b/model-00044-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c761cb2d5540c9332b6e1fbfeada54882794117d96ed4ae5b768546bce234a4 +size 4362142872 diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54d3067088af429e7dee2f4eca918e3bbb284790 --- /dev/null +++ b/model-00045-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d56b0a8a6e5a1d8a921b5de090744b400fd2d7d386a56617467b632283a53fd +size 4362142872 diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa216747b2d6eee2b308f21dc7acae3fcee11dd6 --- /dev/null +++ b/model-00046-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc94b9a43bf7a24fc4e31181dd4f087260767e88a3f6ab5534385cfd084c8b9 +size 4966188880 diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..285de6bdce370d16703ae909e83cb673d514bb06 --- /dev/null +++ b/model-00047-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8681f5d0b98c710b62ade04956a10b701c5c39f84f2e58f9ae4aa739557e009 +size 4362142872 diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9388cda09b14deae38fbacfa71810e8c62a31967 --- /dev/null +++ b/model-00048-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f83074672531e50b8bcb97c85ee93fa5ac0c40795ccc4901435c324cfcec22a +size 4362142872 diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd41fba359effc83ad07fd2b4f4de252607d6dc0 --- /dev/null +++ b/model-00049-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e33c007af158d3d3cd598b39abb1dd96a21f2f26d23e6767a8e5e9bbf2cf27f +size 4966188880 diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f7e1b092a532bee12f2e23c59c556ddac162c9a --- /dev/null +++ b/model-00050-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abfe635947b4cbff59207b7e2cf88a00ff2d2ae59419cda8ccc3ddc8c335147 +size 4362142872 diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a953b51588501d9c3b415c7e0ac5dfeaf34811e --- /dev/null +++ b/model-00051-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8068346da7c225cc880db22291bf299d548c3ff019c13c5c673869e709ac903b +size 4362142872 diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf270452d9aaba7fbe0e86e5623b9e8904ce6cae --- /dev/null +++ b/model-00052-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44adc089eeb3e44f8bd762d2e86f6151924b43e838ee4b7e6abef0c048fd2f2 +size 4966188880 diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e8472b565188ec52e81fd4531bade2129192acf --- /dev/null +++ b/model-00053-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42feb6e069dc4029ee5ce94859b0c2f38c34539404dd5d89127e1eda8e2b18fc +size 4362142872 diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee0012dfc7bc6614d9e32ec3fe05524ea9496e2d --- /dev/null +++ b/model-00054-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003232b2082d0fd12fa396228f7ff52e6597635ac04571f50cae506fce7c1e45 +size 4362142872 diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cb4f2164a3d23c8be0d2625062f6e3b50819e69 --- /dev/null +++ b/model-00055-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec99eb9a6589c5de4e4a1ee2e5970c3be9e500bf90d6a09f9e9c5b2866aed19 +size 4966188880 diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..186a3701d5f4a083850a43b875eb4d91c773de04 --- /dev/null +++ b/model-00056-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200bd71aaa77b575508382df8c0e0b43afdcc34d108dc49bf520dd95d82fca9f +size 4362142872 diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8554f40085275389ac94ee26ca8c77fb21763fdf --- /dev/null +++ b/model-00057-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b648dc4fecb267276468a2ae63ccf84d8fc2cd3d0f6e5c2981ca4758aa0681 +size 4362142872 diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..490112ed52edbd497df0b39275b7fd21eb2aefd8 --- /dev/null +++ b/model-00058-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6593c4b0aec76bd8e1aebb75fa3a16670978440eaf8b7867d2611124a91dd8 +size 4966188880 diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..225ceda6bf404d05da46d2093b4fb3a8bb8dc06c --- /dev/null +++ b/model-00059-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184a3584a07441da5f460a3241808232bc07b724f823ee4ea844ff335bd2804f +size 4362142872 diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f4c65201aeb36fc50e8588472f09d7c2e2153ce --- /dev/null +++ b/model-00060-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16136cfe80586f81e26561ae00b56666a7bbd38577ba622f9f0ed105e1c4698a +size 4362142872 diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b3ac44fb544fe425777261d3e5964d709489c74 --- /dev/null +++ b/model-00061-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b884b01a7d17e691e8b670f3c82e4bb74e484619dc4ed2b83590192e306163d +size 4362241496 diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0a4b0f5791b1ead947fb296ca7ea6ac2100ff99 --- /dev/null +++ b/model-00062-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d0e600549abd9d02a118ae526b3a57511539b1b0bb6dea557cc2cfb43a52e3 +size 4202692736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8aab69e95f0d7da106bad45a4e7c35897ecf3d80 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 282214825984 + }, + "weight_map": { + "lm_head.weight": "model-00062-of-00062.safetensors", + "model.embed_tokens.weight": "model-00001-of-00062.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00062.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-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-00002-of-00062.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00062.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.10.input_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.11.input_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.input_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.13.input_layernorm.weight": "model-00012-of-00062.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00062.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.14.input_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.15.input_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.input_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.17.input_layernorm.weight": "model-00015-of-00062.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00015-of-00062.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.18.input_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.19.input_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.20.input_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.21.input_layernorm.weight": "model-00018-of-00062.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00062.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.22.input_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.23.input_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.input_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.25.input_layernorm.weight": "model-00021-of-00062.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.26.input_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.27.input_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.input_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.29.input_layernorm.weight": "model-00024-of-00062.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.30.input_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.31.input_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.input_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.33.input_layernorm.weight": "model-00027-of-00062.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.34.input_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.35.input_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.input_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.37.input_layernorm.weight": "model-00030-of-00062.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.38.input_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.39.input_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.40.input_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.41.input_layernorm.weight": "model-00033-of-00062.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.42.input_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.43.input_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.input_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.45.input_layernorm.weight": "model-00036-of-00062.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.46.input_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.47.input_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.input_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.49.input_layernorm.weight": "model-00039-of-00062.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00062.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00062.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.50.input_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.51.input_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.input_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.input_layernorm.weight": "model-00042-of-00062.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00042-of-00062.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.54.input_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.55.input_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.input_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.input_layernorm.weight": "model-00045-of-00062.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00045-of-00062.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.58.input_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.59.input_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.60.input_layernorm.weight": "model-00047-of-00062.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00047-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.q_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.61.input_layernorm.weight": "model-00048-of-00062.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00048-of-00062.safetensors", + "model.layers.61.self_attn.k_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.q_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.input_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.input_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.input_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.64.self_attn.k_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.q_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.65.input_layernorm.weight": "model-00051-of-00062.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", + "model.layers.65.self_attn.k_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.q_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.input_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.input_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.input_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.68.self_attn.k_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.q_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.69.input_layernorm.weight": "model-00054-of-00062.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", + "model.layers.69.self_attn.k_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.q_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.70.input_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.70.self_attn.k_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.q_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.71.input_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.post_attention_layernorm.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.q_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.input_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.73.input_layernorm.weight": "model-00057-of-00062.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00057-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.q_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.74.input_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.74.self_attn.k_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.q_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.75.input_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.post_attention_layernorm.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.75.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.input_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.77.input_layernorm.weight": "model-00060-of-00062.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", + "model.layers.77.self_attn.k_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.q_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.78.input_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.78.self_attn.k_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.q_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.79.input_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.post_attention_layernorm.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.q_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00062.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00062.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", + "model.norm.weight": "model-00061-of-00062.safetensors" + } +}