diff --git a/README.md b/README.md index bfa6ca627a71d48fe20dd2a45b1484f401477680..298377e065c5e92ca055019e4b33489e3ad34388 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,7 @@ tags: - unsloth - llama - trl +- sft license: apache-2.0 language: - en diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..919819cd672a742bc1da08175cad25a7be8c1687 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "_name_or_path": "unsloth/Llama-3.3-70B-Instruct-bnb-4bit", + "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, + "pad_token_id": 128004, + "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": "4.46.3", + "unsloth_fixed": true, + "unsloth_version": "2024.12.4", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..650def6b8db4800761cedac5c5cdec44c4d94189 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "max_length": 131072, + "pad_token_id": 128004, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.3" +} diff --git a/model-00001-of-00061.safetensors b/model-00001-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08976fafb9fb343e760656a5cf863df397cdcfcd --- /dev/null +++ b/model-00001-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f06c3445375fa31d92fde9cf3d2c5a176377d3b7d5556ffbbc6f068926abef +size 4584375104 diff --git a/model-00002-of-00061.safetensors b/model-00002-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d81a373afb5a8bd64d0b3a9657266f332a4d28f --- /dev/null +++ b/model-00002-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600a10bd2c756f57ec7ff2260b44466ceac32fe686e62058898b51f4bb8e883b +size 4966123352 diff --git a/model-00003-of-00061.safetensors b/model-00003-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc3f452be8d6ae7e53d4172fb4fd00f66debda43 --- /dev/null +++ b/model-00003-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b6c6fb29eca0081d83015c38e01f5f8982cc450e3d0c20f73582245691259f +size 4362110112 diff --git a/model-00004-of-00061.safetensors b/model-00004-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1279cd8372b931ec41ee0e261724eb6d52fff8b --- /dev/null +++ b/model-00004-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95518c033a3db3432bdbbee30db94f6d9b03b5609044be81cab93d65702c406 +size 4362110104 diff --git a/model-00005-of-00061.safetensors b/model-00005-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c49aef193bc1f04c33f4c195776122f4edabdf83 --- /dev/null +++ b/model-00005-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f03ea61c140c0fa0eb8b1c72291efa81c4cdd79ab2d1915309bf1f0beab917 +size 4966123352 diff --git a/model-00006-of-00061.safetensors b/model-00006-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9301bad9a87760919a9ac3a8deeaaa19bd0ebcc --- /dev/null +++ b/model-00006-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae7fd27a478f158fc571747165e0c910c23370710a37deb949ac6c5333dca58 +size 4362110112 diff --git a/model-00007-of-00061.safetensors b/model-00007-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56f41657587c8bc68fedcbf9dc3967254bbd5a76 --- /dev/null +++ b/model-00007-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ca9153770626b5c2d310db809fe36629a614541d1e1776b8e4d5c0fc1816bb +size 4362110104 diff --git a/model-00008-of-00061.safetensors b/model-00008-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0cb726e1088fdb524339cf29b09daecb9f421b18 --- /dev/null +++ b/model-00008-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf180ca16e8811fd716d4361f66646649176a4a0f1fb62185c12dfc640f1cbe6 +size 4966123344 diff --git a/model-00009-of-00061.safetensors b/model-00009-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e938bbe00931fd0d2b9d9d0db0947ce81d7bcda7 --- /dev/null +++ b/model-00009-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3eafede44f0b32ab45323219f10596227b02bc6435f224d55347cd6e1132f84 +size 4362110120 diff --git a/model-00010-of-00061.safetensors b/model-00010-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..178e7da830a3e291bbb8e4cd39affc9bf93f2ea3 --- /dev/null +++ b/model-00010-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d923fbd5c0bc207346307c52d7634f08a4fcd4457ea350779c670c34c2529d60 +size 4362110120 diff --git a/model-00011-of-00061.safetensors b/model-00011-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5777de73352df369b1da7c9de80f7154eaedc264 --- /dev/null +++ b/model-00011-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d092d302a0ad2934df30d9044a8fd3fcaa952e8d4ba8ab9ba6c434d39d6b1ae4 +size 4966123368 diff --git a/model-00012-of-00061.safetensors b/model-00012-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1cdb641257f362d97c45aaff45ba3692140b563d --- /dev/null +++ b/model-00012-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b29f86f8927a5b2f9d3cb82a6cafc1f7234527e691e350dc81da6e7512313cc +size 4362110120 diff --git a/model-00013-of-00061.safetensors b/model-00013-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f50a4949ab91b99ae862bd797c512634a83dc8b2 --- /dev/null +++ b/model-00013-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817c94af6dc7b6f062af3898f0faabb36e57a87915d8188521f25b126fe13924 +size 4362110120 diff --git a/model-00014-of-00061.safetensors b/model-00014-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42d15fa95db5ab60a934fc9e411077d785ddcbe3 --- /dev/null +++ b/model-00014-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf21c80e158af52d90ead220fd267bfd8828f718cabf79f73b626a9f243c486f +size 4966123368 diff --git a/model-00015-of-00061.safetensors b/model-00015-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7fbf99d19fae8f5391c0efdaf899e45e1f46f701 --- /dev/null +++ b/model-00015-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202f5bcfb5420fae56b4e4e893dbb52d36d3e87f041fdf036bad0e76d4dfdda2 +size 4362110120 diff --git a/model-00016-of-00061.safetensors b/model-00016-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d87fa371050e391d2b8d821fee000c67b4c2585 --- /dev/null +++ b/model-00016-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ccd01dc18787c1f72309905c4d620e18833a1a2588eec598b77d003c45b1ca +size 4362110120 diff --git a/model-00017-of-00061.safetensors b/model-00017-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76581f97aa9538e60551e008a7c14296f501a688 --- /dev/null +++ b/model-00017-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3a31d44ce9b32a4086b46558cc7e70eed25b45ab3bd4c09ca0464838285ffd +size 4966123368 diff --git a/model-00018-of-00061.safetensors b/model-00018-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ce26f70ddcb8b1ff4aa409d429e875a5b6ed9bb --- /dev/null +++ b/model-00018-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e615257ea1f9223e127482397a37e4d1e0d1c09e705c37b9ba9afa257a17d2 +size 4362110120 diff --git a/model-00019-of-00061.safetensors b/model-00019-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e814e73dbff98c82f31733656b88ffef048a6ac1 --- /dev/null +++ b/model-00019-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db8844e7d26de9d76ee6e02e1a2681cd433910b7f012d9c9865d8cccbb9f4ff3 +size 4362110120 diff --git a/model-00020-of-00061.safetensors b/model-00020-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cba0d1c8b3df4b758ee712c9c40245258bf34cb8 --- /dev/null +++ b/model-00020-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c336c46aca34e6ce677a7d7a94eadfbe18cca3c2f84d24f8ad1afa23237552 +size 4966123368 diff --git a/model-00021-of-00061.safetensors b/model-00021-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3657525c40e327a0a9b82311d114091173ba3b4b --- /dev/null +++ b/model-00021-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee4db0091248a838ad8586a0122dbd2c59967bd544197f8cc6bd8c452de172d +size 4362110120 diff --git a/model-00022-of-00061.safetensors b/model-00022-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c31799032530e723f6c893ea546496b01e2bd36b --- /dev/null +++ b/model-00022-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6cc6b562906b459fc1fc630437c378d85328bcee3ca315689cb212cb0cb0c5 +size 4362110120 diff --git a/model-00023-of-00061.safetensors b/model-00023-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d451a854a9b034c2fb8f748911c9defc5c3629b6 --- /dev/null +++ b/model-00023-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a51a597d1f5814c21fc439bcc0d1e2184ba3c436331a2627ca67032fc6898ba +size 4966123368 diff --git a/model-00024-of-00061.safetensors b/model-00024-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f1623b0fc33873dac272aeac07dcfa77f95c260 --- /dev/null +++ b/model-00024-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878737db20f26f179a27bd70ccca8b61a33e4698158ab345372383cbe5ce9dae +size 4362110120 diff --git a/model-00025-of-00061.safetensors b/model-00025-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e88f44d936cf7a2d1e7ec87af7448b07c22f96a8 --- /dev/null +++ b/model-00025-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4213ee4d985a1f53eca503ace2af0c3c2873ca45a66ab5e861d0bdec12c6a7a8 +size 4362110120 diff --git a/model-00026-of-00061.safetensors b/model-00026-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2de8d83cf6ef2806c8e0735947fe68877f7db2a5 --- /dev/null +++ b/model-00026-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c644a1dbb4b63cd6dd7e773b56d059879e2ce604ab9476347c1e1452e9dee76e +size 4966123368 diff --git a/model-00027-of-00061.safetensors b/model-00027-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9022eb7916c2e686d026c6290726097764324ac5 --- /dev/null +++ b/model-00027-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d01101a7797fde2b463c3b165258db23ff947a19f8813b7815281ba9637369 +size 4362110120 diff --git a/model-00028-of-00061.safetensors b/model-00028-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..393c80de3835e907c9f2ade9765402450f506cb1 --- /dev/null +++ b/model-00028-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6cc99e8fd0f02a6a3af3035c9e8ef0e314c4e7fbc3943cf6a6ea9027766dd4 +size 4362110120 diff --git a/model-00029-of-00061.safetensors b/model-00029-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b88ecf04372d6b56fbb4be3590e2a92ed62b55e --- /dev/null +++ b/model-00029-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c291f214bd9efe020cbccc7981456166c86900ae6d05e98081623d9e5c446c9 +size 4966123368 diff --git a/model-00030-of-00061.safetensors b/model-00030-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42e0a4b141eb5f87d2f92ea6bebd04c483dd2fc9 --- /dev/null +++ b/model-00030-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a136cf6116d74ff28a53463c2773e2e4c42f57f50eb64c75c5d5d6dbe324b1d +size 4362110120 diff --git a/model-00031-of-00061.safetensors b/model-00031-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10fd9f324d7a5407deec9d632bd2ed4348db2b42 --- /dev/null +++ b/model-00031-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0877c94c5aebeafd0d8bfb9bafba66876fea5fa5ddd9b61fd4f4450505d33d24 +size 4362110120 diff --git a/model-00032-of-00061.safetensors b/model-00032-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..078e00ceff97d28233f6e9c0777dd1b28f34b8b2 --- /dev/null +++ b/model-00032-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66553bdd47ae92b4cfeb66ce69ee0b219ca7bc010080135253df26c19a1942f6 +size 4966123368 diff --git a/model-00033-of-00061.safetensors b/model-00033-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8382114d40e61e6c59798359fbe736736f0ab1c3 --- /dev/null +++ b/model-00033-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1144165098eaf0ceb72b9e460cd98b01dd8046d7ebbb68ceb2adcb4ad1706c +size 4362110120 diff --git a/model-00034-of-00061.safetensors b/model-00034-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99af688ef417c6b260e6717c4bfcd505111e9919 --- /dev/null +++ b/model-00034-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67f276ce200477adbf93204ec099b6d2322abfaf7bd57ae1290a0b32051831d +size 4362110120 diff --git a/model-00035-of-00061.safetensors b/model-00035-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e044cb1282c2dc2ebdbf65cc7c6297ba70de5a43 --- /dev/null +++ b/model-00035-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad70bbe2ce2e5bae8d1984db6ed1e6e9ec7438b6b094078de393996b5fc371e +size 4966123368 diff --git a/model-00036-of-00061.safetensors b/model-00036-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5de9ffec2139973000e20522d0556b0e1f2c478e --- /dev/null +++ b/model-00036-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007ec2a21e83a1d6e2a040bfa5657f044ea4076f4f66c01f1635df0d1dd6d4a2 +size 4362110120 diff --git a/model-00037-of-00061.safetensors b/model-00037-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..40f948bc4e1a7a14f393ccfeec310d2f7c924558 --- /dev/null +++ b/model-00037-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52abefa32d54233fe2712882b391bf33138e69bcb96e114df23a9f78abf71b37 +size 4362110120 diff --git a/model-00038-of-00061.safetensors b/model-00038-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..859c8a95f79e8811e574cd960ef2906f95105dd6 --- /dev/null +++ b/model-00038-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4682a32d9d9d58b76c0ceeaaa045f67a1e2eef41438b7e17f91f6502e6908281 +size 4966123368 diff --git a/model-00039-of-00061.safetensors b/model-00039-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4471b4cdd1395ecbc0b4ac214f412bb8945afcb9 --- /dev/null +++ b/model-00039-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5b2e3b5bb7ceb72ac94e1ffd20e456d6a07559d47f26bb1f536223cc67a957 +size 4362110120 diff --git a/model-00040-of-00061.safetensors b/model-00040-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b801f2c0a2e8f11915bfcbf9304f5cf370671012 --- /dev/null +++ b/model-00040-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b8fd64e15db0f6277afc54959fc2cab21bbba6d219adfef480ef9347d946ea +size 4362110120 diff --git a/model-00041-of-00061.safetensors b/model-00041-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f31dc5104adc07fcdff010c2b23bbf121596cfd5 --- /dev/null +++ b/model-00041-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29e896662b19b2416ea05b0f67ae34a1696fb039d3f8ddd86eaf7db9fe7856c +size 4966123368 diff --git a/model-00042-of-00061.safetensors b/model-00042-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d3e1363c22cdca3b64777ba94e1ca0530b97954 --- /dev/null +++ b/model-00042-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3d420305fb40590aeac15f4f9078584b046e0913420a57363b1c1be81c57e0 +size 4362110120 diff --git a/model-00043-of-00061.safetensors b/model-00043-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca9c77346a0fc03387fbad318f497fa9ef1cea3b --- /dev/null +++ b/model-00043-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5172c70c5dfdbef12779ba0d5c9cb26769cf532172bee288eca182ab8fdfec +size 4362110120 diff --git a/model-00044-of-00061.safetensors b/model-00044-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3470a9785b46a2b9352a5fa629d399787838904 --- /dev/null +++ b/model-00044-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f65ba0834720ec1e33c26e2addf38572338e0305dd925121b7c3f70abe51b6 +size 4966123368 diff --git a/model-00045-of-00061.safetensors b/model-00045-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd76113aaa8f4b5ae8d4b67985513af772286a11 --- /dev/null +++ b/model-00045-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd14a3d853f8f00e8e25eae0a94d70aee8619cc6a5d5dec742dab2d06b0d5586 +size 4362110120 diff --git a/model-00046-of-00061.safetensors b/model-00046-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e7de53183be375056a6f2997c8f9a8fd9884193b --- /dev/null +++ b/model-00046-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd3a3fdd9739853866ca0b2fb414acb2c509a486ae5cdc6bc7d32afd77baac8 +size 4362110120 diff --git a/model-00047-of-00061.safetensors b/model-00047-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b6c440d6dcf871bb7077f0d3e76e210ccddbb46 --- /dev/null +++ b/model-00047-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e53e7a8566c184933834abecdaac9a7b3af7b0e70930b5067c0ce235f0f020 +size 4966123368 diff --git a/model-00048-of-00061.safetensors b/model-00048-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a67269741ab16f471936e87aded38b569092101e --- /dev/null +++ b/model-00048-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ba373c2e99340a63ee6845d978a3c3eea8b77c0e434da682763267178cabac +size 4362110120 diff --git a/model-00049-of-00061.safetensors b/model-00049-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1f3d6a0533ecef6ec03a25e3bcd6338f9b18d05 --- /dev/null +++ b/model-00049-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb61c3032935071689edf452bb58e112924af494f37b86c583d280b99fc90ae +size 4362110120 diff --git a/model-00050-of-00061.safetensors b/model-00050-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2a7a1126fdd2afcef7e32c4700d024bd4fbdec2 --- /dev/null +++ b/model-00050-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f002585f6158bfbb0761ad9973472fe7c5b3ef73ceb55457aa9925e3c885d890 +size 4966123368 diff --git a/model-00051-of-00061.safetensors b/model-00051-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df88568f06bdc55077085251d42bd787cbcaf79d --- /dev/null +++ b/model-00051-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc4769b3b85a7d0a48f4e70eaa3c9af4fbdae60eaa10d205f13e2410ba9e64b +size 4362110120 diff --git a/model-00052-of-00061.safetensors b/model-00052-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df84fa2433a9a54c8fb91ad61ed946e8f8e4d625 --- /dev/null +++ b/model-00052-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea297f1b7b6961e38a259f37c801e00667f2f81a926ed4764aa7216ecd94276 +size 4362110120 diff --git a/model-00053-of-00061.safetensors b/model-00053-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d80ced62650d6ce028b847fe7c007ae2e53c66f --- /dev/null +++ b/model-00053-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27aaa45547ee5991dbe996091e958845809d33acf99d405adae6437eef8220a9 +size 4966123368 diff --git a/model-00054-of-00061.safetensors b/model-00054-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16ebe6ebf94fced1bc12a559240240b80883700b --- /dev/null +++ b/model-00054-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee1e3811c6996148768b44f3aedad5408b94ed5b730073baa58f0f65d528990 +size 4362110120 diff --git a/model-00055-of-00061.safetensors b/model-00055-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73acb41fd9993108e8e188ce9f30ecc84cf9a61b --- /dev/null +++ b/model-00055-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3057c2e18a97786430d15f73151477839877e21cadc6f54a63e46ac2240ad26b +size 4362110120 diff --git a/model-00056-of-00061.safetensors b/model-00056-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..672ed8104d1c68e49e2ec34a699880adecc1fe12 --- /dev/null +++ b/model-00056-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca81d46e6a687a4e8dc689f971fdcbad5c1f25f485e7cc4c476a439dba522cf +size 4966123368 diff --git a/model-00057-of-00061.safetensors b/model-00057-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b18efcc22097ab6e8d49f756b11b10210516f8de --- /dev/null +++ b/model-00057-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4015b0cfb49f537c9bf356cc75ca4a11848478bac5357d66ad56c6d5fb1d87f5 +size 4362110120 diff --git a/model-00058-of-00061.safetensors b/model-00058-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35bff582a53e739097196bbaba40ad004ecc75e9 --- /dev/null +++ b/model-00058-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09adc1c0f18be5ffe2d9339de6a3b18a64010689e9e772fa6a30d74bd5e2c436 +size 4362110120 diff --git a/model-00059-of-00061.safetensors b/model-00059-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7652a440387b873b73615023d61784065c48eff3 --- /dev/null +++ b/model-00059-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2e4a5382a7247ae2355e533fd5f57106dc890dfb71b403c0489cf54b0a9b4e +size 4966123368 diff --git a/model-00060-of-00061.safetensors b/model-00060-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc4cc170579ad4bef4484fc20b1dd99532a78ea9 --- /dev/null +++ b/model-00060-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb0e0ef464325f2570a25f1f56bdd5b750385800dc156b9a1810b69eb1f7571 +size 4362110120 diff --git a/model-00061-of-00061.safetensors b/model-00061-of-00061.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6f552b71bcac3d0b748ff1cf0726f72d1b15b68 --- /dev/null +++ b/model-00061-of-00061.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9c2e1566ba0d701fe987034ddb7a427a72082f4cb8c735c3fa5de0d36713f8 +size 3980444328 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..778a8010627e3c0acd5af136a571278431dd1f9d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 278009495552 + }, + "weight_map": { + "lm_head.weight": "model-00061-of-00061.safetensors", + "model.embed_tokens.weight": "model-00001-of-00061.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00061.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00061.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00061.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00061.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.10.input_layernorm.weight": "model-00009-of-00061.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00061.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.11.input_layernorm.weight": "model-00010-of-00061.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00061.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00061.safetensors", + "model.layers.12.input_layernorm.weight": "model-00011-of-00061.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00061.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00061.safetensors", + "model.layers.13.input_layernorm.weight": "model-00011-of-00061.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.14.input_layernorm.weight": "model-00012-of-00061.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00012-of-00061.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00061.safetensors", + "model.layers.15.input_layernorm.weight": "model-00013-of-00061.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00013-of-00061.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00061.safetensors", + "model.layers.16.input_layernorm.weight": "model-00014-of-00061.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00061.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00061.safetensors", + "model.layers.17.input_layernorm.weight": "model-00014-of-00061.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.18.input_layernorm.weight": "model-00015-of-00061.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00015-of-00061.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00061.safetensors", + "model.layers.19.input_layernorm.weight": "model-00016-of-00061.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00016-of-00061.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00061.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00061.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00061.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00061.safetensors", + "model.layers.20.input_layernorm.weight": "model-00017-of-00061.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00017-of-00061.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00061.safetensors", + "model.layers.21.input_layernorm.weight": "model-00017-of-00061.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.22.input_layernorm.weight": "model-00018-of-00061.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00061.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00017-of-00061.safetensors", + "model.layers.23.input_layernorm.weight": "model-00019-of-00061.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00061.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00061.safetensors", + "model.layers.24.input_layernorm.weight": "model-00020-of-00061.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00061.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00061.safetensors", + "model.layers.25.input_layernorm.weight": "model-00020-of-00061.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.26.input_layernorm.weight": "model-00021-of-00061.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00021-of-00061.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00020-of-00061.safetensors", + "model.layers.27.input_layernorm.weight": "model-00022-of-00061.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00022-of-00061.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00061.safetensors", + "model.layers.28.input_layernorm.weight": "model-00023-of-00061.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00061.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00061.safetensors", + "model.layers.29.input_layernorm.weight": "model-00023-of-00061.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00061.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00061.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00061.safetensors", + "model.layers.30.input_layernorm.weight": "model-00024-of-00061.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00024-of-00061.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00023-of-00061.safetensors", + "model.layers.31.input_layernorm.weight": "model-00025-of-00061.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00061.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00024-of-00061.safetensors", + "model.layers.32.input_layernorm.weight": "model-00026-of-00061.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00026-of-00061.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00061.safetensors", + "model.layers.33.input_layernorm.weight": "model-00026-of-00061.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.34.input_layernorm.weight": "model-00027-of-00061.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00027-of-00061.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00026-of-00061.safetensors", + "model.layers.35.input_layernorm.weight": "model-00028-of-00061.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00028-of-00061.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00027-of-00061.safetensors", + "model.layers.36.input_layernorm.weight": "model-00029-of-00061.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00029-of-00061.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00028-of-00061.safetensors", + "model.layers.37.input_layernorm.weight": "model-00029-of-00061.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.38.input_layernorm.weight": "model-00030-of-00061.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00030-of-00061.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00029-of-00061.safetensors", + "model.layers.39.input_layernorm.weight": "model-00031-of-00061.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00031-of-00061.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00030-of-00061.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00061.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00061.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00061.safetensors", + "model.layers.40.input_layernorm.weight": "model-00032-of-00061.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00032-of-00061.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00031-of-00061.safetensors", + "model.layers.41.input_layernorm.weight": "model-00032-of-00061.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.42.input_layernorm.weight": "model-00033-of-00061.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00033-of-00061.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00032-of-00061.safetensors", + "model.layers.43.input_layernorm.weight": "model-00034-of-00061.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00034-of-00061.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00033-of-00061.safetensors", + "model.layers.44.input_layernorm.weight": "model-00035-of-00061.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00035-of-00061.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00034-of-00061.safetensors", + "model.layers.45.input_layernorm.weight": "model-00035-of-00061.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.46.input_layernorm.weight": "model-00036-of-00061.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00036-of-00061.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00035-of-00061.safetensors", + "model.layers.47.input_layernorm.weight": "model-00037-of-00061.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00037-of-00061.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00036-of-00061.safetensors", + "model.layers.48.input_layernorm.weight": "model-00038-of-00061.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00038-of-00061.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00037-of-00061.safetensors", + "model.layers.49.input_layernorm.weight": "model-00038-of-00061.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00061.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.50.input_layernorm.weight": "model-00039-of-00061.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00039-of-00061.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00038-of-00061.safetensors", + "model.layers.51.input_layernorm.weight": "model-00040-of-00061.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00040-of-00061.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00039-of-00061.safetensors", + "model.layers.52.input_layernorm.weight": "model-00041-of-00061.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00041-of-00061.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00040-of-00061.safetensors", + "model.layers.53.input_layernorm.weight": "model-00041-of-00061.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.54.input_layernorm.weight": "model-00042-of-00061.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00042-of-00061.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00041-of-00061.safetensors", + "model.layers.55.input_layernorm.weight": "model-00043-of-00061.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00043-of-00061.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00042-of-00061.safetensors", + "model.layers.56.input_layernorm.weight": "model-00044-of-00061.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00044-of-00061.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00043-of-00061.safetensors", + "model.layers.57.input_layernorm.weight": "model-00044-of-00061.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.58.input_layernorm.weight": "model-00045-of-00061.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00045-of-00061.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00044-of-00061.safetensors", + "model.layers.59.input_layernorm.weight": "model-00046-of-00061.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00046-of-00061.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00045-of-00061.safetensors", + "model.layers.6.input_layernorm.weight": "model-00006-of-00061.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00061.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00061.safetensors", + "model.layers.60.input_layernorm.weight": "model-00047-of-00061.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00047-of-00061.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00061.safetensors", + "model.layers.61.input_layernorm.weight": "model-00047-of-00061.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.62.input_layernorm.weight": "model-00048-of-00061.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00048-of-00061.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00047-of-00061.safetensors", + "model.layers.63.input_layernorm.weight": "model-00049-of-00061.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00049-of-00061.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00048-of-00061.safetensors", + "model.layers.64.input_layernorm.weight": "model-00050-of-00061.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00050-of-00061.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00061.safetensors", + "model.layers.65.input_layernorm.weight": "model-00050-of-00061.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.66.input_layernorm.weight": "model-00051-of-00061.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00051-of-00061.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00050-of-00061.safetensors", + "model.layers.67.input_layernorm.weight": "model-00052-of-00061.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00052-of-00061.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00051-of-00061.safetensors", + "model.layers.68.input_layernorm.weight": "model-00053-of-00061.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00053-of-00061.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00061.safetensors", + "model.layers.69.input_layernorm.weight": "model-00053-of-00061.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00061.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00061.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00061.safetensors", + "model.layers.70.input_layernorm.weight": "model-00054-of-00061.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00054-of-00061.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00053-of-00061.safetensors", + "model.layers.71.input_layernorm.weight": "model-00055-of-00061.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00061.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00054-of-00061.safetensors", + "model.layers.72.input_layernorm.weight": "model-00056-of-00061.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00061.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00055-of-00061.safetensors", + "model.layers.73.input_layernorm.weight": "model-00056-of-00061.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.74.input_layernorm.weight": "model-00057-of-00061.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00057-of-00061.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00056-of-00061.safetensors", + "model.layers.75.input_layernorm.weight": "model-00058-of-00061.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00061.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00057-of-00061.safetensors", + "model.layers.76.input_layernorm.weight": "model-00059-of-00061.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00061.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00058-of-00061.safetensors", + "model.layers.77.input_layernorm.weight": "model-00059-of-00061.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.78.input_layernorm.weight": "model-00060-of-00061.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00060-of-00061.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00059-of-00061.safetensors", + "model.layers.79.input_layernorm.weight": "model-00061-of-00061.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00061-of-00061.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00061.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00060-of-00061.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00061.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00061.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00061.safetensors", + "model.layers.9.input_layernorm.weight": "model-00008-of-00061.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00061.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00061.safetensors", + "model.norm.weight": "model-00061-of-00061.safetensors" + } +}