diff --git a/ckpt_25/config.json b/ckpt_25/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e5cf5208fcec62cfa8c1ddc338dff189b430712a --- /dev/null +++ b/ckpt_25/config.json @@ -0,0 +1,47 @@ +{ + "architectures": [ + "LlavaForConditionalGeneration" + ], + "ignore_index": -100, + "image_token_index": 32022, + "model_type": "llava", + "projector_hidden_act": "gelu", + "text_config": { + "_name_or_path": "LLM360/K2-Chat", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": null, + "hidden_size": 8192, + "intermediate_size": 22016, + "max_position_embeddings": 8192, + "max_sequence_length": 8192, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 64, + "pad_token_id": 0, + "rms_norm_eps": 1e-05, + "rope_theta": 500000.0, + "torch_dtype": "float16", + "vocab_size": 32032 + }, + "torch_dtype": "float32", + "transformers_version": "4.42.4", + "vision_config": { + "architectures": [ + "CLIPVisionModel" + ], + "dropout": 0.0, + "hidden_size": 1024, + "image_size": 336, + "intermediate_size": 4096, + "model_type": "clip_vision_model", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "patch_size": 14, + "projection_dim": 768 + }, + "vision_feature_layer": -2, + "vision_feature_select_strategy": "default" +} diff --git a/ckpt_25/generation_config.json b/ckpt_25/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f093df1a757821ca6c8614512eb8caf66a005777 --- /dev/null +++ b/ckpt_25/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.42.4" +} diff --git a/ckpt_25/model-00001-of-00055.safetensors b/ckpt_25/model-00001-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dc8e083c939e298c4d1f19108aebf373174d6df --- /dev/null +++ b/ckpt_25/model-00001-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0667aacf9e350e36103782df8864069df519511960add96ddfba2f500bee7a5 +size 4360926752 diff --git a/ckpt_25/model-00002-of-00055.safetensors b/ckpt_25/model-00002-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec189d90ea8c511c6b8806c4ae9238ca0e0efc24 --- /dev/null +++ b/ckpt_25/model-00002-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16543d3930e9bb7510c91679a696feab9cfc1116d250b5175dbfaf7e81913139 +size 4949411632 diff --git a/ckpt_25/model-00003-of-00055.safetensors b/ckpt_25/model-00003-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca0b25bda3ad65a2962563a6eec5e3ab7a6dff3b --- /dev/null +++ b/ckpt_25/model-00003-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8267375a314083573dc5fe2610c61cfc61e04baadcf8c7479fc853ee68488ade +size 4764796592 diff --git a/ckpt_25/model-00004-of-00055.safetensors b/ckpt_25/model-00004-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92b6af6c23cae2bf39e08fba31c37cd01e74d672 --- /dev/null +++ b/ckpt_25/model-00004-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c07973e8cb37180d884f39b756421e2635efa1a5dc8e4ee29925a3130b53a8b +size 4949411632 diff --git a/ckpt_25/model-00005-of-00055.safetensors b/ckpt_25/model-00005-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d5bb6a16c470380dad4a0c508994db915dc1490 --- /dev/null +++ b/ckpt_25/model-00005-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:415d89c5b74576f94d3e4d4e7fdb7a0f9f67de2c74eda9afc6f16d8777792538 +size 4764796592 diff --git a/ckpt_25/model-00006-of-00055.safetensors b/ckpt_25/model-00006-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e20f5607a659a1ffa993d4c251b1857a84db521c --- /dev/null +++ b/ckpt_25/model-00006-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06be1a72b1b1413fc814c0f4cd4c072ba737110e3e11f26c28aff92c56b028d8 +size 4949411632 diff --git a/ckpt_25/model-00007-of-00055.safetensors b/ckpt_25/model-00007-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0288354440901087b98861b886148288ce58ad49 --- /dev/null +++ b/ckpt_25/model-00007-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c7974008d1801545c1f40cc64d0574f20d74632f3ab210cfa1df7992981854 +size 4764796592 diff --git a/ckpt_25/model-00008-of-00055.safetensors b/ckpt_25/model-00008-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c7305dae4d50c7fec2ece127ba6e5ac0403f47e --- /dev/null +++ b/ckpt_25/model-00008-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67954a0bf4f5fce221588bea8dbe9336e4e5c4e7d207d7b88cc944b78c9c30d0 +size 4949411640 diff --git a/ckpt_25/model-00009-of-00055.safetensors b/ckpt_25/model-00009-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1b2b25a81e3415bfdefbedda76488276ee28d75 --- /dev/null +++ b/ckpt_25/model-00009-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb08d8c30ccc0f795c525c32a0cae7c244267fd19aee893dcba7733321193c2 +size 4764796608 diff --git a/ckpt_25/model-00010-of-00055.safetensors b/ckpt_25/model-00010-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59bc9b7c03e4d782e6122018e36756cabe03b8d5 --- /dev/null +++ b/ckpt_25/model-00010-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73de5cef2924e7e5de7fb3a42e425a55400e8219e6f5896178a96f960dfc5e89 +size 4949411640 diff --git a/ckpt_25/model-00011-of-00055.safetensors b/ckpt_25/model-00011-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5147cf14e3401d0b6649e2bdf90bf170e9f8503e --- /dev/null +++ b/ckpt_25/model-00011-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d46e58469a03c3ab6db4105c9c7cf183bf420e5f04037a9b435fd0a1b42313f6 +size 4764796608 diff --git a/ckpt_25/model-00012-of-00055.safetensors b/ckpt_25/model-00012-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..917b5672ce92c7f3a468ae0413ca2196e75840e4 --- /dev/null +++ b/ckpt_25/model-00012-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97166cf49d0c5571e41a82a05810585775970f16b205b7de4a11328fdd232874 +size 4949411640 diff --git a/ckpt_25/model-00013-of-00055.safetensors b/ckpt_25/model-00013-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6508a178753aa7c01ceb1eedcd0d53672c0d8bd --- /dev/null +++ b/ckpt_25/model-00013-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c11c89f330079dfdbd12abc0dc9174cbb6bb64cbb958da0bfab5082df341c759 +size 4764796608 diff --git a/ckpt_25/model-00014-of-00055.safetensors b/ckpt_25/model-00014-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e866242a4077570baca5241a83e13ed4e5908e00 --- /dev/null +++ b/ckpt_25/model-00014-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:648257a952490f1661cad4cf948a28b5a6b061ac6fc10f5f5fa6eddbd215b360 +size 4949411640 diff --git a/ckpt_25/model-00015-of-00055.safetensors b/ckpt_25/model-00015-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d6d42ae0e0058215454f89430cdf862d7ae86fa --- /dev/null +++ b/ckpt_25/model-00015-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f97a962785ba665830fab2c8aa7ba4e2e76526f96df99436602fe854ab81b2 +size 4764796608 diff --git a/ckpt_25/model-00016-of-00055.safetensors b/ckpt_25/model-00016-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a9f1184adfad56116c3033f7d4bd135315e5d97 --- /dev/null +++ b/ckpt_25/model-00016-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4d72e41753dc3d5ef38dc9f147ac96df7b21b1b16d175ad6191918e4093bac +size 4949411640 diff --git a/ckpt_25/model-00017-of-00055.safetensors b/ckpt_25/model-00017-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d96b67503d38164698ca40a5c231f2a7880db19d --- /dev/null +++ b/ckpt_25/model-00017-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041391cfa5a83893f38d5b1d3744d32606cfb6c807d405b84f494e9a1f4bfdf7 +size 4764796608 diff --git a/ckpt_25/model-00018-of-00055.safetensors b/ckpt_25/model-00018-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a738e502b61b85ce500c71cac8a45aeb76b9be35 --- /dev/null +++ b/ckpt_25/model-00018-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3cd79fca1b356179850673e42f58eadef059513077f49eecd2516735111dda3 +size 4949411640 diff --git a/ckpt_25/model-00019-of-00055.safetensors b/ckpt_25/model-00019-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea89d16fbd565c365776c9a180806e867a76ab68 --- /dev/null +++ b/ckpt_25/model-00019-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d199b682ceffe099b9dff4b98fc28d586ff1da997980f3668a07684c645b39bb +size 4764796608 diff --git a/ckpt_25/model-00020-of-00055.safetensors b/ckpt_25/model-00020-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a15325740436966fe3281bfc02eacd0bdeb2c4bf --- /dev/null +++ b/ckpt_25/model-00020-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2226faf3079d19e5f129db9dd0ddbbc599debb0cb46c16b60608deedc86de983 +size 4949411640 diff --git a/ckpt_25/model-00021-of-00055.safetensors b/ckpt_25/model-00021-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a90d6528e021bc7c3a18f355458db650d77b6ed --- /dev/null +++ b/ckpt_25/model-00021-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849459a7fdcf394ad2db52634ee652bd8db20dffe7ac78dc4a1ca0462288c6f7 +size 4764796608 diff --git a/ckpt_25/model-00022-of-00055.safetensors b/ckpt_25/model-00022-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b705aedde06bf9c2275c040566fc5fdab0ecc89 --- /dev/null +++ b/ckpt_25/model-00022-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df60e141ae60dc0e5c115abe04158b67957b9922178eba1d32b7d46382a05bb3 +size 4949411640 diff --git a/ckpt_25/model-00023-of-00055.safetensors b/ckpt_25/model-00023-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..65b122bc18ad8f1cac31e6b11fd3674ea228f758 --- /dev/null +++ b/ckpt_25/model-00023-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b7f346704b42affaa183739156107fcd9920c27674eb4050d2064e76e16c2b +size 4764796608 diff --git a/ckpt_25/model-00024-of-00055.safetensors b/ckpt_25/model-00024-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ea1544a7ea92ddb3295b898406958b2bce23691 --- /dev/null +++ b/ckpt_25/model-00024-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5c3021c10374384c302ece1e03a86697aa90014394cd1b853ae94cb34adc06 +size 4949411640 diff --git a/ckpt_25/model-00025-of-00055.safetensors b/ckpt_25/model-00025-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..117793088af7efa5ddbacf86ac035089520bbe2d --- /dev/null +++ b/ckpt_25/model-00025-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c80b32df7d82472a0271fd13dfc6afc0206c7e20bb261aebb3ee87e5e502315 +size 4764796608 diff --git a/ckpt_25/model-00026-of-00055.safetensors b/ckpt_25/model-00026-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d35f8f3a43f1eba616088b70c9a84f5ebe2a114c --- /dev/null +++ b/ckpt_25/model-00026-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dc30a2173f5bc925a287b344780220488f7c53e8bb10669c0348bcb1635bf8 +size 4949411640 diff --git a/ckpt_25/model-00027-of-00055.safetensors b/ckpt_25/model-00027-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..040ae33aa3d468dfffbd706513b5c3a2388b42c6 --- /dev/null +++ b/ckpt_25/model-00027-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f5b0450bcde68b7422afe85e8596b8e7db7f439cd8ee872bebb4a0eb2a40af +size 4764796608 diff --git a/ckpt_25/model-00028-of-00055.safetensors b/ckpt_25/model-00028-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e0fd009657c7dc6ac9b2053171242b170a8e28a --- /dev/null +++ b/ckpt_25/model-00028-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6133b4f87510724a660c3cb4ff0448f744ca08c14199ed03d7d8f5bc5f5965 +size 4949411640 diff --git a/ckpt_25/model-00029-of-00055.safetensors b/ckpt_25/model-00029-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16d13eb4bec8d4374811aa5e721d7df69cdb48d9 --- /dev/null +++ b/ckpt_25/model-00029-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb4e15e2f6c9e7842de695dfbb58da1866b8f363f0f93c8cd263b71da052a73 +size 4764796608 diff --git a/ckpt_25/model-00030-of-00055.safetensors b/ckpt_25/model-00030-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2f9cbb39dd46d09f184deec125b64e7b30af8dd --- /dev/null +++ b/ckpt_25/model-00030-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc4d0be5cfc673211559aaa93f492f95847a72a22d3c5b7c3bf39307b58f813 +size 4949411640 diff --git a/ckpt_25/model-00031-of-00055.safetensors b/ckpt_25/model-00031-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ca3cccf1fb299c3bbf6934026cff8f01c2b87dc --- /dev/null +++ b/ckpt_25/model-00031-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbf0c1a4027251013733fc05edcadc04c52ab2ca85ba010dd0a97c92d7734b5 +size 4764796608 diff --git a/ckpt_25/model-00032-of-00055.safetensors b/ckpt_25/model-00032-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7668214551cf1cac30b4550eb875b4ee1fa6726 --- /dev/null +++ b/ckpt_25/model-00032-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45e0bb93d76a416f60bf0fb4c5962896639a596fdd7a6602d0aa0914c1ed3723 +size 4949411640 diff --git a/ckpt_25/model-00033-of-00055.safetensors b/ckpt_25/model-00033-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..65e3e2863c5b4960f7ebe0f8218ff714ec75e15d --- /dev/null +++ b/ckpt_25/model-00033-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906e505c2afa06966eed6d3bedf34576ae18611e7c088c62a20521f5c67d9d64 +size 4764796608 diff --git a/ckpt_25/model-00034-of-00055.safetensors b/ckpt_25/model-00034-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1fe7224ed2ff289722a38abb1ad6224cc9c6321c --- /dev/null +++ b/ckpt_25/model-00034-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9705528151672abe0290d3bdaafd2e91117abcc51af1918eecf4627a660a376e +size 4949411640 diff --git a/ckpt_25/model-00035-of-00055.safetensors b/ckpt_25/model-00035-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5388f84d4d00da905921a1f9b417277ceea37072 --- /dev/null +++ b/ckpt_25/model-00035-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c484fb999237da1a57e3640ed6bca722f9c6fb66ae966d2bf6b73b039eaaa8 +size 4764796608 diff --git a/ckpt_25/model-00036-of-00055.safetensors b/ckpt_25/model-00036-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1137473f66305781a5fd5d315c073423172b2cf0 --- /dev/null +++ b/ckpt_25/model-00036-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309cc269543f0dc504ec158cc7b4393d0c501b70b7ced25d352b1ba6734afbe3 +size 4949411640 diff --git a/ckpt_25/model-00037-of-00055.safetensors b/ckpt_25/model-00037-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c42079060e5c27894a795f6ad167dcd1e5866b12 --- /dev/null +++ b/ckpt_25/model-00037-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549341ba16cdcf7beeeecc473adc6e6401d4add39bbcfa13beaee91325cd9433 +size 4764796608 diff --git a/ckpt_25/model-00038-of-00055.safetensors b/ckpt_25/model-00038-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..30f1212ee3cf270c3b4bfc932670278d96cefbdd --- /dev/null +++ b/ckpt_25/model-00038-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcda6737835d92b21bb169e78d6d4b872ca4efb28117c8a78817a90daea55493 +size 4949411640 diff --git a/ckpt_25/model-00039-of-00055.safetensors b/ckpt_25/model-00039-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5dc03bd443d87c8039a5794b3991a0e21e966d82 --- /dev/null +++ b/ckpt_25/model-00039-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f120a2f0ac643f68a69c2e9c8f83b41e2627806a699df8acf60f76c249b7a19 +size 4764796608 diff --git a/ckpt_25/model-00040-of-00055.safetensors b/ckpt_25/model-00040-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6d0fb3f9018633de71aaae900ef4844e53145f1 --- /dev/null +++ b/ckpt_25/model-00040-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b451685c15f914f50dc19571d40f1a1a0e0afe381466b51a94d2c50a5dca2511 +size 4949411640 diff --git a/ckpt_25/model-00041-of-00055.safetensors b/ckpt_25/model-00041-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..261d5632d0215311cb7475f95d5d432866e82769 --- /dev/null +++ b/ckpt_25/model-00041-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f08ef64d6ca88fdaf29203e697ac26320caaa29b4f21b22dbf06be6019c8f75f +size 4764796608 diff --git a/ckpt_25/model-00042-of-00055.safetensors b/ckpt_25/model-00042-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d3d4a77a9348b6696c60baa3ccd3813778dbfaf2 --- /dev/null +++ b/ckpt_25/model-00042-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74ec96300d322d89ecab2dc9065bc462c11a99b70748c25540ac23affbf9e4d +size 4949411640 diff --git a/ckpt_25/model-00043-of-00055.safetensors b/ckpt_25/model-00043-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..357fccd50d2f06fddb4a44a34f2e4606d7469a63 --- /dev/null +++ b/ckpt_25/model-00043-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc43881eaac83f5aef8d3b7c7ac3d9f20cd654127d2b51aa7dbe7fb36238e54a +size 4764796608 diff --git a/ckpt_25/model-00044-of-00055.safetensors b/ckpt_25/model-00044-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ae39aba6d9482dbb640c7a21c5b25dd5e416e2f6 --- /dev/null +++ b/ckpt_25/model-00044-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27918d2402742dacd9f82c530c35e9426f13c27ddddeb56786552c3e41fa8b39 +size 4949411640 diff --git a/ckpt_25/model-00045-of-00055.safetensors b/ckpt_25/model-00045-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4371779519a3978785cfa0c65bcd3711e10fb889 --- /dev/null +++ b/ckpt_25/model-00045-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751a45d4e7925c508833bddeac250c2a396ee76b526fde7167b45f68dfd90f09 +size 4764796608 diff --git a/ckpt_25/model-00046-of-00055.safetensors b/ckpt_25/model-00046-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a75967c1df02bb6049503e00876694979be3097 --- /dev/null +++ b/ckpt_25/model-00046-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b8f20f5d02faee0761b4aa4c752e215659791c4b6c3c6dc490e4bbdd4d9430 +size 4949411640 diff --git a/ckpt_25/model-00047-of-00055.safetensors b/ckpt_25/model-00047-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8fac9991090ba1a55d67a82e673763ab5507fa6 --- /dev/null +++ b/ckpt_25/model-00047-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad3b39bb399be0c112335f52d47c60d63e7d88379fd29f344fcb51bdd804903 +size 4764796608 diff --git a/ckpt_25/model-00048-of-00055.safetensors b/ckpt_25/model-00048-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8ebf721e01337383b5d95aea5554c2b025e7599 --- /dev/null +++ b/ckpt_25/model-00048-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6570f145f5de57c9e6ac307f644ca8adad2583e58cc18f03515155e3bf2e7973 +size 4949411640 diff --git a/ckpt_25/model-00049-of-00055.safetensors b/ckpt_25/model-00049-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66abb719f62aa79a55f36e0d59c07c0a51b007ee --- /dev/null +++ b/ckpt_25/model-00049-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b932bf599839604f5cb40fdc0a13944cf62848fd9c08f2a740e5b1225e16c2c +size 4764796608 diff --git a/ckpt_25/model-00050-of-00055.safetensors b/ckpt_25/model-00050-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df51ad17818719b505e8c6c67f3b9be382b9005d --- /dev/null +++ b/ckpt_25/model-00050-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291bba67a5fc8180bb6071e8e5847a011db84acb89d8405999fdaf5e18609245 +size 4949411640 diff --git a/ckpt_25/model-00051-of-00055.safetensors b/ckpt_25/model-00051-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af332b30840e99a933adf0807e4a29cd3b232911 --- /dev/null +++ b/ckpt_25/model-00051-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd910ee5895fe66be8f3209d29549f354bc55e39ea687656bceea20454b756cb +size 4764796608 diff --git a/ckpt_25/model-00052-of-00055.safetensors b/ckpt_25/model-00052-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58ee9dbc1899d0e71337cc919d38e076b07011ed --- /dev/null +++ b/ckpt_25/model-00052-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a36c635f32b2592be4bed58ce06107e0e235555c531ec7cb5d94c8f89b1a27 +size 4949411640 diff --git a/ckpt_25/model-00053-of-00055.safetensors b/ckpt_25/model-00053-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0f8a82b21023e89bca19a960f373d9d9982c449 --- /dev/null +++ b/ckpt_25/model-00053-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6853e4b606ed832cec5798f4c208e31d957e74564ff23d7e752e5e1df5583fd6 +size 4764796608 diff --git a/ckpt_25/model-00054-of-00055.safetensors b/ckpt_25/model-00054-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20684a4b5d31298d776e83890cb2c63d847af547 --- /dev/null +++ b/ckpt_25/model-00054-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda3a30c32b294894e3dfe5a8685c30e5de82b04f1b51ecc62b237123309dc9d +size 4681008928 diff --git a/ckpt_25/model-00055-of-00055.safetensors b/ckpt_25/model-00055-of-00055.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f42016a7175d0231cc1288838fd9a4f270481c46 --- /dev/null +++ b/ckpt_25/model-00055-of-00055.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a618fec38530c46fd0cd90e9ba0e5f28d38e9b91d3298f80dc184ddbf34a53 +size 1049624720 diff --git a/ckpt_25/model.safetensors.index.json b/ckpt_25/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..6fc04ac4d7d7a0777fec33cc30515816554e1135 --- /dev/null +++ b/ckpt_25/model.safetensors.index.json @@ -0,0 +1,1125 @@ +{ + "metadata": { + "total_size": 262660825088 + }, + "weight_map": { + "language_model.lm_head.weight": "model-00055-of-00055.safetensors", + "language_model.model.embed_tokens.weight": "model-00001-of-00055.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00055.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00055.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.mlp.down_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.mlp.gate_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.mlp.up_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.mlp.down_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.mlp.gate_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.mlp.up_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.12.mlp.down_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.12.mlp.gate_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.12.mlp.up_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00009-of-00055.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.mlp.down_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.mlp.gate_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.mlp.up_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.mlp.down_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.mlp.gate_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.mlp.up_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00010-of-00055.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.15.mlp.down_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.15.mlp.gate_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.15.mlp.up_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00011-of-00055.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.mlp.down_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.mlp.gate_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.mlp.up_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.mlp.down_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.mlp.gate_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.mlp.up_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00012-of-00055.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.18.mlp.down_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.18.mlp.gate_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.18.mlp.up_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.18.self_attn.o_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight": "model-00013-of-00055.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.mlp.down_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.mlp.gate_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.mlp.up_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00055.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.mlp.down_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.mlp.gate_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.mlp.up_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00014-of-00055.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.21.mlp.down_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.21.mlp.gate_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.21.mlp.up_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00015-of-00055.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.mlp.down_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.mlp.gate_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.mlp.up_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.mlp.down_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.mlp.gate_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.mlp.up_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00016-of-00055.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.24.mlp.down_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.24.mlp.gate_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.24.mlp.up_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00017-of-00055.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.mlp.down_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.mlp.gate_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.mlp.up_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.mlp.down_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.mlp.gate_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.mlp.up_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00018-of-00055.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.27.mlp.down_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.27.mlp.gate_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.27.mlp.up_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00019-of-00055.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.mlp.down_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.mlp.gate_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.mlp.up_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.self_attn.o_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.mlp.down_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.mlp.gate_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.mlp.up_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00020-of-00055.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.3.mlp.down_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.3.mlp.gate_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.3.mlp.up_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00055.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.30.mlp.down_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.30.mlp.gate_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.30.mlp.up_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.30.post_attention_layernorm.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.30.self_attn.o_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight": "model-00021-of-00055.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.mlp.down_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.mlp.gate_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.mlp.up_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.post_attention_layernorm.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.32.input_layernorm.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.mlp.down_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.mlp.gate_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.mlp.up_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.post_attention_layernorm.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.self_attn.k_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.self_attn.o_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.32.self_attn.q_proj.weight": "model-00022-of-00055.safetensors", + "language_model.model.layers.32.self_attn.v_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.33.input_layernorm.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.33.mlp.down_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.33.mlp.gate_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.33.mlp.up_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.33.post_attention_layernorm.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.33.self_attn.k_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.33.self_attn.o_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.33.self_attn.q_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.33.self_attn.v_proj.weight": "model-00023-of-00055.safetensors", + "language_model.model.layers.34.input_layernorm.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.mlp.down_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.mlp.gate_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.mlp.up_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.post_attention_layernorm.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.self_attn.k_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.self_attn.o_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.self_attn.q_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.34.self_attn.v_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.35.input_layernorm.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.mlp.down_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.mlp.gate_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.mlp.up_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.post_attention_layernorm.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight": "model-00024-of-00055.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.36.input_layernorm.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.36.mlp.down_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.36.mlp.gate_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.36.mlp.up_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.36.post_attention_layernorm.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.36.self_attn.k_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.36.self_attn.o_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.36.self_attn.q_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.36.self_attn.v_proj.weight": "model-00025-of-00055.safetensors", + "language_model.model.layers.37.input_layernorm.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.mlp.down_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.mlp.gate_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.mlp.up_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.post_attention_layernorm.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.self_attn.k_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.self_attn.o_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.self_attn.q_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.37.self_attn.v_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.38.input_layernorm.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.mlp.down_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.mlp.gate_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.mlp.up_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.post_attention_layernorm.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.self_attn.k_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.self_attn.o_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.38.self_attn.q_proj.weight": "model-00026-of-00055.safetensors", + "language_model.model.layers.38.self_attn.v_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.39.input_layernorm.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.39.mlp.down_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.39.mlp.gate_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.39.mlp.up_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.39.post_attention_layernorm.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight": "model-00027-of-00055.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.mlp.down_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.mlp.gate_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.mlp.up_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.40.input_layernorm.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.mlp.down_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.mlp.gate_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.mlp.up_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.post_attention_layernorm.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.self_attn.k_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.self_attn.o_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.self_attn.q_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.40.self_attn.v_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.41.input_layernorm.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.mlp.down_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.mlp.gate_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.mlp.up_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.post_attention_layernorm.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.self_attn.k_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.self_attn.o_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.41.self_attn.q_proj.weight": "model-00028-of-00055.safetensors", + "language_model.model.layers.41.self_attn.v_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.42.input_layernorm.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.42.mlp.down_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.42.mlp.gate_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.42.mlp.up_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.42.post_attention_layernorm.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.42.self_attn.k_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.42.self_attn.o_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.42.self_attn.q_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.42.self_attn.v_proj.weight": "model-00029-of-00055.safetensors", + "language_model.model.layers.43.input_layernorm.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.mlp.down_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.mlp.gate_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.mlp.up_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.post_attention_layernorm.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.self_attn.k_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.self_attn.o_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.self_attn.q_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.43.self_attn.v_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.44.input_layernorm.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.mlp.down_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.mlp.gate_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.mlp.up_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.post_attention_layernorm.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.self_attn.k_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.self_attn.o_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.44.self_attn.q_proj.weight": "model-00030-of-00055.safetensors", + "language_model.model.layers.44.self_attn.v_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.45.input_layernorm.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.45.mlp.down_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.45.mlp.gate_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.45.mlp.up_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.45.post_attention_layernorm.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.45.self_attn.k_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.45.self_attn.o_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.45.self_attn.q_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.45.self_attn.v_proj.weight": "model-00031-of-00055.safetensors", + "language_model.model.layers.46.input_layernorm.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.mlp.down_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.mlp.gate_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.mlp.up_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.post_attention_layernorm.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.self_attn.k_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.self_attn.o_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.self_attn.q_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.46.self_attn.v_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.47.input_layernorm.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.mlp.down_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.mlp.gate_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.mlp.up_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.post_attention_layernorm.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.self_attn.k_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.self_attn.o_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.47.self_attn.q_proj.weight": "model-00032-of-00055.safetensors", + "language_model.model.layers.47.self_attn.v_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.48.input_layernorm.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.48.mlp.down_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.48.mlp.gate_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.48.mlp.up_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.48.post_attention_layernorm.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.48.self_attn.k_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.48.self_attn.o_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.48.self_attn.q_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.48.self_attn.v_proj.weight": "model-00033-of-00055.safetensors", + "language_model.model.layers.49.input_layernorm.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.mlp.down_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.mlp.gate_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.mlp.up_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.post_attention_layernorm.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.self_attn.k_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.self_attn.o_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.self_attn.q_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.49.self_attn.v_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.mlp.down_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.mlp.gate_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.mlp.up_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00004-of-00055.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.50.input_layernorm.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.mlp.down_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.mlp.gate_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.mlp.up_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.post_attention_layernorm.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.self_attn.k_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.self_attn.o_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.50.self_attn.q_proj.weight": "model-00034-of-00055.safetensors", + "language_model.model.layers.50.self_attn.v_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.51.input_layernorm.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.51.mlp.down_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.51.mlp.gate_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.51.mlp.up_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.51.post_attention_layernorm.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.51.self_attn.k_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.51.self_attn.o_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.51.self_attn.q_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.51.self_attn.v_proj.weight": "model-00035-of-00055.safetensors", + "language_model.model.layers.52.input_layernorm.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.mlp.down_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.mlp.gate_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.mlp.up_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.post_attention_layernorm.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.self_attn.k_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.self_attn.o_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.self_attn.q_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.52.self_attn.v_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.53.input_layernorm.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.mlp.down_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.mlp.gate_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.mlp.up_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.post_attention_layernorm.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.self_attn.k_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.self_attn.o_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.53.self_attn.q_proj.weight": "model-00036-of-00055.safetensors", + "language_model.model.layers.53.self_attn.v_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.54.input_layernorm.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.54.mlp.down_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.54.mlp.gate_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.54.mlp.up_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.54.post_attention_layernorm.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.54.self_attn.k_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.54.self_attn.o_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.54.self_attn.q_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.54.self_attn.v_proj.weight": "model-00037-of-00055.safetensors", + "language_model.model.layers.55.input_layernorm.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.mlp.down_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.mlp.gate_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.mlp.up_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.post_attention_layernorm.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.self_attn.k_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.self_attn.o_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.self_attn.q_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.55.self_attn.v_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.56.input_layernorm.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.mlp.down_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.mlp.gate_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.mlp.up_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.post_attention_layernorm.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.self_attn.k_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.self_attn.o_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.56.self_attn.q_proj.weight": "model-00038-of-00055.safetensors", + "language_model.model.layers.56.self_attn.v_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.57.input_layernorm.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.57.mlp.down_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.57.mlp.gate_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.57.mlp.up_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.57.post_attention_layernorm.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.57.self_attn.k_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.57.self_attn.o_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.57.self_attn.q_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.57.self_attn.v_proj.weight": "model-00039-of-00055.safetensors", + "language_model.model.layers.58.input_layernorm.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.mlp.down_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.mlp.gate_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.mlp.up_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.post_attention_layernorm.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.self_attn.k_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.self_attn.o_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.self_attn.q_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.58.self_attn.v_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.59.input_layernorm.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.mlp.down_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.mlp.gate_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.mlp.up_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.post_attention_layernorm.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.self_attn.k_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.self_attn.o_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.59.self_attn.q_proj.weight": "model-00040-of-00055.safetensors", + "language_model.model.layers.59.self_attn.v_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.6.mlp.down_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.6.mlp.gate_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.6.mlp.up_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00005-of-00055.safetensors", + "language_model.model.layers.60.input_layernorm.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.60.mlp.down_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.60.mlp.gate_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.60.mlp.up_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.60.post_attention_layernorm.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.60.self_attn.k_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.60.self_attn.o_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.60.self_attn.q_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.60.self_attn.v_proj.weight": "model-00041-of-00055.safetensors", + "language_model.model.layers.61.input_layernorm.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.mlp.down_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.mlp.gate_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.mlp.up_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.post_attention_layernorm.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.self_attn.k_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.self_attn.o_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.self_attn.q_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.61.self_attn.v_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.62.input_layernorm.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.mlp.down_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.mlp.gate_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.mlp.up_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.post_attention_layernorm.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.self_attn.k_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.self_attn.o_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.62.self_attn.q_proj.weight": "model-00042-of-00055.safetensors", + "language_model.model.layers.62.self_attn.v_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.63.input_layernorm.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.63.mlp.down_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.63.mlp.gate_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.63.mlp.up_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.63.post_attention_layernorm.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.63.self_attn.k_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.63.self_attn.o_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.63.self_attn.q_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.63.self_attn.v_proj.weight": "model-00043-of-00055.safetensors", + "language_model.model.layers.64.input_layernorm.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.mlp.down_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.mlp.gate_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.mlp.up_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.post_attention_layernorm.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.self_attn.k_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.self_attn.o_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.self_attn.q_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.64.self_attn.v_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.65.input_layernorm.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.mlp.down_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.mlp.gate_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.mlp.up_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.post_attention_layernorm.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.self_attn.k_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.self_attn.o_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.65.self_attn.q_proj.weight": "model-00044-of-00055.safetensors", + "language_model.model.layers.65.self_attn.v_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.66.input_layernorm.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.66.mlp.down_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.66.mlp.gate_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.66.mlp.up_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.66.post_attention_layernorm.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.66.self_attn.k_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.66.self_attn.o_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.66.self_attn.q_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.66.self_attn.v_proj.weight": "model-00045-of-00055.safetensors", + "language_model.model.layers.67.input_layernorm.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.mlp.down_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.mlp.gate_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.mlp.up_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.post_attention_layernorm.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.self_attn.k_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.self_attn.o_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.self_attn.q_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.67.self_attn.v_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.68.input_layernorm.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.mlp.down_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.mlp.gate_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.mlp.up_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.post_attention_layernorm.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.self_attn.k_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.self_attn.o_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.68.self_attn.q_proj.weight": "model-00046-of-00055.safetensors", + "language_model.model.layers.68.self_attn.v_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.69.input_layernorm.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.69.mlp.down_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.69.mlp.gate_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.69.mlp.up_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.69.post_attention_layernorm.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.69.self_attn.k_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.69.self_attn.o_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.69.self_attn.q_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.69.self_attn.v_proj.weight": "model-00047-of-00055.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.mlp.down_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.mlp.gate_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.mlp.up_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.70.input_layernorm.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.mlp.down_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.mlp.gate_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.mlp.up_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.post_attention_layernorm.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.self_attn.k_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.self_attn.o_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.self_attn.q_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.70.self_attn.v_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.71.input_layernorm.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.mlp.down_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.mlp.gate_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.mlp.up_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.post_attention_layernorm.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.self_attn.k_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.self_attn.o_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.71.self_attn.q_proj.weight": "model-00048-of-00055.safetensors", + "language_model.model.layers.71.self_attn.v_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.72.input_layernorm.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.72.mlp.down_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.72.mlp.gate_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.72.mlp.up_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.72.post_attention_layernorm.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.72.self_attn.k_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.72.self_attn.o_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.72.self_attn.q_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.72.self_attn.v_proj.weight": "model-00049-of-00055.safetensors", + "language_model.model.layers.73.input_layernorm.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.mlp.down_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.mlp.gate_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.mlp.up_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.post_attention_layernorm.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.self_attn.k_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.self_attn.o_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.self_attn.q_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.73.self_attn.v_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.74.input_layernorm.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.mlp.down_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.mlp.gate_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.mlp.up_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.post_attention_layernorm.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.self_attn.k_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.self_attn.o_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.74.self_attn.q_proj.weight": "model-00050-of-00055.safetensors", + "language_model.model.layers.74.self_attn.v_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.75.input_layernorm.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.75.mlp.down_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.75.mlp.gate_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.75.mlp.up_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.75.post_attention_layernorm.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.75.self_attn.k_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.75.self_attn.o_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.75.self_attn.q_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.75.self_attn.v_proj.weight": "model-00051-of-00055.safetensors", + "language_model.model.layers.76.input_layernorm.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.mlp.down_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.mlp.gate_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.mlp.up_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.post_attention_layernorm.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.self_attn.k_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.self_attn.o_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.self_attn.q_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.76.self_attn.v_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.77.input_layernorm.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.mlp.down_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.mlp.gate_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.mlp.up_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.post_attention_layernorm.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.self_attn.k_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.self_attn.o_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.77.self_attn.q_proj.weight": "model-00052-of-00055.safetensors", + "language_model.model.layers.77.self_attn.v_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.78.input_layernorm.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.78.mlp.down_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.78.mlp.gate_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.78.mlp.up_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.78.post_attention_layernorm.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.78.self_attn.k_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.78.self_attn.o_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.78.self_attn.q_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.78.self_attn.v_proj.weight": "model-00053-of-00055.safetensors", + "language_model.model.layers.79.input_layernorm.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.mlp.down_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.mlp.gate_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.mlp.up_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.post_attention_layernorm.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.self_attn.k_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.self_attn.o_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.self_attn.q_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.79.self_attn.v_proj.weight": "model-00054-of-00055.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.mlp.down_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.mlp.gate_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.mlp.up_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00006-of-00055.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.9.mlp.down_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.9.mlp.gate_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.9.mlp.up_proj.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00008-of-00055.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00007-of-00055.safetensors", + "language_model.model.norm.weight": "model-00054-of-00055.safetensors", + "multi_modal_projector.linear_1.bias": "model-00001-of-00055.safetensors", + "multi_modal_projector.linear_1.weight": "model-00001-of-00055.safetensors", + "multi_modal_projector.linear_2.bias": "model-00001-of-00055.safetensors", + "multi_modal_projector.linear_2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00055.safetensors", + "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00055.safetensors" + } +}