diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..19727155b7493cab38b90516c4a7eed96ab7412a --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,5 @@ +{ + "<|model|>": 32002, + "<|system|>": 32000, + "<|user|>": 32001 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ae4b9368a15b8085b59c49a0f032379fa48acc --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "/root/models/alpindale_goliath-120b", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 137, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.35.1", + "use_cache": false, + "vocab_size": 32003 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ff27dfcd352035fa795d384dac77c8f14f18c8ad --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.35.1" +} diff --git a/pytorch_model-00001-of-00050.bin b/pytorch_model-00001-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..43776f3c93bd8def4e998cd7465f88e8ba719a88 --- /dev/null +++ b/pytorch_model-00001-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0644e402464deecd7bffd5825922d8049dc320c1e706f8c72e9f6e1cdbec0744 +size 4718715602 diff --git a/pytorch_model-00002-of-00050.bin b/pytorch_model-00002-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..28dc53f03baca42d8cf022941249bd32030cd248 --- /dev/null +++ b/pytorch_model-00002-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b627a9f81821160e266c157fa968a44edb2109b73906b9e67cc436ec5734cd +size 4664173854 diff --git a/pytorch_model-00003-of-00050.bin b/pytorch_model-00003-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..38f5ec00c779963ad8901c9c74ceb82089a88262 --- /dev/null +++ b/pytorch_model-00003-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9407718f06330f0a25c90fc555f1ebfde5d1b0e99ceb744891622de6e97fdcf +size 4999718222 diff --git a/pytorch_model-00004-of-00050.bin b/pytorch_model-00004-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..cdb4961f434e9e51cfc9bef8c4071c422171bbf6 --- /dev/null +++ b/pytorch_model-00004-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a422d6799705c6a52258989aa96a6a99f2b950877c7ee3b1ee79b3f53fbe3d +size 4966163202 diff --git a/pytorch_model-00005-of-00050.bin b/pytorch_model-00005-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..248ae52b17d2480b58f1a3c28276fe9e7de80be9 --- /dev/null +++ b/pytorch_model-00005-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e118e1b9b4e87b55b4d86739ed8bca8484424489e901c9a85d6cabcf2e081c1 +size 4664140510 diff --git a/pytorch_model-00006-of-00050.bin b/pytorch_model-00006-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..1a553570f15b832ebf13cfa27f49f6ab1daa9570 --- /dev/null +++ b/pytorch_model-00006-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8830606b9afc7c50f4eb666b122a46a0bf7a7c09d98feef85055472ec4b8c4ad +size 4664173918 diff --git a/pytorch_model-00007-of-00050.bin b/pytorch_model-00007-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..d265756fbde07c7da8c1cfa145ef41b247e24f56 --- /dev/null +++ b/pytorch_model-00007-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69eabbfaa0df6da242ab1e39c5d382fd2234a8e78194377b11009f9d70d456d +size 4664173918 diff --git a/pytorch_model-00008-of-00050.bin b/pytorch_model-00008-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8e18b6a766f4c13d7354f211b911fd71cd7a00e --- /dev/null +++ b/pytorch_model-00008-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0afd1aa2cab4ee8d3f23c4c29d12de3bb17ec0d55962709ebd0ea4e42e338f13 +size 4999718286 diff --git a/pytorch_model-00009-of-00050.bin b/pytorch_model-00009-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..673f2871710ae80107703b960e3a054748cb7b66 --- /dev/null +++ b/pytorch_model-00009-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2ff5766531b73751213a49b5a9d6e63ef69d2bd0f514452fa2fa9f6bc7e3151 +size 4966163202 diff --git a/pytorch_model-00010-of-00050.bin b/pytorch_model-00010-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f0f28d7b609f91cc0443abf590b0ee9ddcfe69d --- /dev/null +++ b/pytorch_model-00010-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10055a381f7248ba3eb26aa0c57afa798e042c9298e06a3cf85f56fa7661f16c +size 4664140510 diff --git a/pytorch_model-00011-of-00050.bin b/pytorch_model-00011-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6648b0e1c9b5a67bf285c3ce18f09c9f4f2d276 --- /dev/null +++ b/pytorch_model-00011-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba0fee2e4ade8f270a42efd56fb5576eae936aa32eb74939dfddfe6d35b969b1 +size 4664173918 diff --git a/pytorch_model-00012-of-00050.bin b/pytorch_model-00012-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..11fdee849383a489693236665367a17de40e90fc --- /dev/null +++ b/pytorch_model-00012-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b0ef1c2fba24f43056b9bc2cb14060222dc1f0f9201686b480956f4f5d449c +size 4664173918 diff --git a/pytorch_model-00013-of-00050.bin b/pytorch_model-00013-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f0de825caea1b0fed1e2074223c091cd6ef9b3a --- /dev/null +++ b/pytorch_model-00013-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da794fba8d6c5ea150190ab642ac55aac1a5522d72b5bd1d2c1eeecf6f4918c3 +size 4999718286 diff --git a/pytorch_model-00014-of-00050.bin b/pytorch_model-00014-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..fbd7786611fafe484ff434bfc38bf9661f1c7751 --- /dev/null +++ b/pytorch_model-00014-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e798585c932b0a218dd79eda44c17a1db20aea368719bebb82dd183e0a0942c +size 4966163202 diff --git a/pytorch_model-00015-of-00050.bin b/pytorch_model-00015-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..ccdcd35164f5d885f6227a58d920fda6473000e1 --- /dev/null +++ b/pytorch_model-00015-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0561b9c31c109124404bf1e006776d19f8acff877ceccbb9ed55f228ba6823e8 +size 4664140510 diff --git a/pytorch_model-00016-of-00050.bin b/pytorch_model-00016-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..dcc43fc2198ab40e6a49f8931930e862c20b8e5f --- /dev/null +++ b/pytorch_model-00016-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5fc263009169b72942267f0a507a5b4c283682783f71cc364522dd2cebd984 +size 4664173918 diff --git a/pytorch_model-00017-of-00050.bin b/pytorch_model-00017-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..415811733830e38c7fbcc3c97860c2ac7e5b9db0 --- /dev/null +++ b/pytorch_model-00017-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e086b89ba2548086b16b781477a3134049cde2284757d220c7acb85b58ba8f8 +size 4664173918 diff --git a/pytorch_model-00018-of-00050.bin b/pytorch_model-00018-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2e6a41daa5fe9a46e5b43cebc0672f72bf00e25 --- /dev/null +++ b/pytorch_model-00018-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97b55b716d8365f3c671112d63d667c66e235dfb5d3c498a7aec9d3991da4f6 +size 4999718286 diff --git a/pytorch_model-00019-of-00050.bin b/pytorch_model-00019-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..0db6505e4016e30d1dd403a554b081627ee10f2d --- /dev/null +++ b/pytorch_model-00019-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f50a08db1ce0363233442e4985aa92a337e1b834d5e5a1e7e3e06d0c0d15912 +size 4966163202 diff --git a/pytorch_model-00020-of-00050.bin b/pytorch_model-00020-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc720de1448453d5f4115aef925c79793953dbb0 --- /dev/null +++ b/pytorch_model-00020-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc8351fc7f96f6a86f7a041a190008d6aa78b08b67df7476a8285243a88a17e +size 4664140510 diff --git a/pytorch_model-00021-of-00050.bin b/pytorch_model-00021-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..749d79ec3338c0764e025f2f31a923ad10421dfe --- /dev/null +++ b/pytorch_model-00021-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3ecba76930394b088c9481c841036bf045e5485054014271658cc548d1989a +size 4664173918 diff --git a/pytorch_model-00022-of-00050.bin b/pytorch_model-00022-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..737ed06db0a38243991f1ab34410c33aa148e315 --- /dev/null +++ b/pytorch_model-00022-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3a82943e0860271f9c37e1c5ad8b5595d447e47c317a75b04225091fa0ba78e +size 4664173918 diff --git a/pytorch_model-00023-of-00050.bin b/pytorch_model-00023-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..853edf9e962576ed54061d491cb3b3db8a915381 --- /dev/null +++ b/pytorch_model-00023-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b6006294dfcf02679f718d46699f60d0c1c2014fb7d706168aa6de0e30dfcf +size 4999718286 diff --git a/pytorch_model-00024-of-00050.bin b/pytorch_model-00024-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd1923469c227ef7467db78af99b2c8f6add3cf3 --- /dev/null +++ b/pytorch_model-00024-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b444823bc7a1cc0bb38a31fd5e20153ab3647daf1e3066605a9b921c19c34c71 +size 4966163202 diff --git a/pytorch_model-00025-of-00050.bin b/pytorch_model-00025-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9c6642e04a51cd620669d6edac29bb92cab60e1 --- /dev/null +++ b/pytorch_model-00025-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14040194deb32126c5be5b5fa7b6dc2b3f8069956b1b34e0bad2642fc4009cb3 +size 4664140510 diff --git a/pytorch_model-00026-of-00050.bin b/pytorch_model-00026-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ef6f135797c9b0f87604b8fbd9ad20084e84b50 --- /dev/null +++ b/pytorch_model-00026-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac312abb800eda0d6caca26affb14ab2908c04850c441f8f6c06b6dfa5ccaec +size 4664173918 diff --git a/pytorch_model-00027-of-00050.bin b/pytorch_model-00027-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..049bb86b1ed28c81276c392877303bf37ea82cbb --- /dev/null +++ b/pytorch_model-00027-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0b5eddf5a4cab556e33b0981e6a08d9f4c05a898e4d929a33b141dee273079 +size 4664173918 diff --git a/pytorch_model-00028-of-00050.bin b/pytorch_model-00028-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..98ad7c407e3e48f2d79a4a3c814a154c64948033 --- /dev/null +++ b/pytorch_model-00028-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481fc542dc3242fed6b17b1719c90da8301d72e228f095eb2b63be1f83dd58fb +size 4999718286 diff --git a/pytorch_model-00029-of-00050.bin b/pytorch_model-00029-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a0811ee62066f5e6ddea3af0c7d4aa980ed6942 --- /dev/null +++ b/pytorch_model-00029-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839a3bb50d1bd209c27350e21c0e48a941b0cd7a702e683494b553dd635315eb +size 4966163202 diff --git a/pytorch_model-00030-of-00050.bin b/pytorch_model-00030-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e6024f889057e9b313bde47c9eb6dd9fbb9ccc4 --- /dev/null +++ b/pytorch_model-00030-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7ec437e7ba668ad91f03ac34dc77609853eb38ea9f2255d16752e9902a1f70 +size 4664140510 diff --git a/pytorch_model-00031-of-00050.bin b/pytorch_model-00031-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4862d7fda765ac7a76ec19fdffbc532a8e35b7a --- /dev/null +++ b/pytorch_model-00031-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cac0d7a893e14941e0938ca843038ba0486b5b8d5efad73f3c6434ff7565255 +size 4664173918 diff --git a/pytorch_model-00032-of-00050.bin b/pytorch_model-00032-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..12a2976c42a1bacdc8ba679bc0878f504d13ecb5 --- /dev/null +++ b/pytorch_model-00032-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e18c3d2080c00f8cf4842cacf30e735ab664188e5e828e2b00801b8bcbc902 +size 4664173918 diff --git a/pytorch_model-00033-of-00050.bin b/pytorch_model-00033-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ae3dbff381548802ff50283cddf1a4efc05d007 --- /dev/null +++ b/pytorch_model-00033-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177564c8cce087425ca13ad85a8eec8c7121220c20337b097911b894d8da5987 +size 4999718286 diff --git a/pytorch_model-00034-of-00050.bin b/pytorch_model-00034-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..bdddd2940a1f638c7e2b890f18553183adb1ea76 --- /dev/null +++ b/pytorch_model-00034-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6378bb4e1238c24eb5745a7e6cf34aa3992e270daae7c14104c510f3ccce1ee6 +size 4966163202 diff --git a/pytorch_model-00035-of-00050.bin b/pytorch_model-00035-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..7517463754979869c4210cf135f2f8845b625236 --- /dev/null +++ b/pytorch_model-00035-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53591636439c6c04b8afa93f613916506595e74611e121627b75957fe40f7957 +size 4664140510 diff --git a/pytorch_model-00036-of-00050.bin b/pytorch_model-00036-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..53c3639f2ede9dca425e777660276ba1b203274b --- /dev/null +++ b/pytorch_model-00036-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663c991def7059f612312c31fb4573e41d799f79a4509bdaa3c069c5d7d281a8 +size 4664173918 diff --git a/pytorch_model-00037-of-00050.bin b/pytorch_model-00037-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..534f3433f8c964abfb8b06197d2bea9bd9809b29 --- /dev/null +++ b/pytorch_model-00037-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285cdcbbcfce23cb41d86b6b14ce51a121b5576d63590ba4df1422fb500c72ba +size 4664173918 diff --git a/pytorch_model-00038-of-00050.bin b/pytorch_model-00038-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec578135a52a137ae3d15e802061a186616b98b4 --- /dev/null +++ b/pytorch_model-00038-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df3e6257c2f9ac8f6b832d23985f505ad6333c0010ce85311ad303a1d1b956c +size 4999718286 diff --git a/pytorch_model-00039-of-00050.bin b/pytorch_model-00039-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb96cca9dec8c0e5d026e1c59f42c5fb9f9e709d --- /dev/null +++ b/pytorch_model-00039-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d28c29866b6533a7c97fd49a042d46b5a27f92e0e5e8d6e809640dbe99bae6 +size 4966163266 diff --git a/pytorch_model-00040-of-00050.bin b/pytorch_model-00040-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..5bf12aca4d7c496f895ff798fbf58bda03e0c408 --- /dev/null +++ b/pytorch_model-00040-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c9858ea4c8b3e66848c274f7fae95196f5a93de2d375031cb9ae30135a7351 +size 4664140574 diff --git a/pytorch_model-00041-of-00050.bin b/pytorch_model-00041-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..edfbd889d8ec297ff35c7873f494135469baa160 --- /dev/null +++ b/pytorch_model-00041-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998a61bfbb53960571d4e3e4326d64dd7c3bb2a2fc1b58b2010a107550540b14 +size 4664173918 diff --git a/pytorch_model-00042-of-00050.bin b/pytorch_model-00042-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..047963e5fbdd6a1b3493e72e9460319d23125cb0 --- /dev/null +++ b/pytorch_model-00042-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76bbe15dee6ec2a99d63fed4d0984d69011e6ca88302f6232bce275622a0daa +size 4664173918 diff --git a/pytorch_model-00043-of-00050.bin b/pytorch_model-00043-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..3920736f113df06755fcedfcdb2d09ded3626d24 --- /dev/null +++ b/pytorch_model-00043-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b525f8a1ed7b1c14d69200c5290b0c3227627306c08ec3222c122d5bd4424f +size 4999718286 diff --git a/pytorch_model-00044-of-00050.bin b/pytorch_model-00044-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..7aa786502b593f31a7412cf706c97e3dc4d49b74 --- /dev/null +++ b/pytorch_model-00044-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166e7ff4ba3c409c4d81316c4551396ed83020a34f55c2dbf713611201f3367d +size 4966163266 diff --git a/pytorch_model-00045-of-00050.bin b/pytorch_model-00045-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..e09f11b4718030fddd853f9aa3227d972bc6b683 --- /dev/null +++ b/pytorch_model-00045-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb91b2e2070d136eba1127398fb1797937a05b954b299aa2a7c88efccb0fc3b4 +size 4664140574 diff --git a/pytorch_model-00046-of-00050.bin b/pytorch_model-00046-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d61ba021a420d1cdeed6a6da708af4be0daf016 --- /dev/null +++ b/pytorch_model-00046-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950646e3d16c38c58ed7a8db5ada05099506068048209112304a8a762fa1f6fc +size 4664173918 diff --git a/pytorch_model-00047-of-00050.bin b/pytorch_model-00047-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..8dc6a2c3d10214f9eca28650ec96c8aa22ca7fa1 --- /dev/null +++ b/pytorch_model-00047-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42e1fb1d90d0842892eaa111f1a6afb5fedcef9eac13632fa7f65bda570a3fae +size 4664173918 diff --git a/pytorch_model-00048-of-00050.bin b/pytorch_model-00048-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9ed6339c58f872d4748330bfd8498c59e05b6e5 --- /dev/null +++ b/pytorch_model-00048-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0df54388a75ca139ce391745631a782f6fdc841f30a720a86cd771b2284a08a2 +size 4999718286 diff --git a/pytorch_model-00049-of-00050.bin b/pytorch_model-00049-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..38fd9afcb4e897160418136478e57a6ffbba2dc1 --- /dev/null +++ b/pytorch_model-00049-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f8f2ed1a118c42bb32aae106bb6969bf0e120be2b414e299f8d726e766ba39 +size 4966179924 diff --git a/pytorch_model-00050-of-00050.bin b/pytorch_model-00050-of-00050.bin new file mode 100644 index 0000000000000000000000000000000000000000..19f27d2b766e5f57e357b79293d306f2e4dbeebf --- /dev/null +++ b/pytorch_model-00050-of-00050.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2648958db8a29cf50d92b62e7dd4ff880ba4b4292d0cad9ab50dccc6147d88 +size 524338565 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000000000000000000000000000000000000..9908f2b1b058a9c41a7a36d0ede10fb61bcfc780 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,1243 @@ +{ + "metadata": { + "total_size": 235497996288 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00050-of-00050.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.100.input_layernorm.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.100.mlp.down_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.100.mlp.gate_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.100.mlp.up_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.100.post_attention_layernorm.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.100.self_attn.k_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.100.self_attn.o_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.100.self_attn.q_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.100.self_attn.v_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.101.input_layernorm.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.mlp.down_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.mlp.gate_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.mlp.up_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.post_attention_layernorm.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.self_attn.k_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.self_attn.o_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.self_attn.q_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.101.self_attn.v_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.input_layernorm.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.mlp.down_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.mlp.gate_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.mlp.up_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.post_attention_layernorm.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.self_attn.k_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.self_attn.o_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.self_attn.q_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.102.self_attn.v_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.103.input_layernorm.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.103.mlp.down_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.103.mlp.gate_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.103.mlp.up_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.103.post_attention_layernorm.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.103.self_attn.k_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.103.self_attn.o_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.103.self_attn.q_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.103.self_attn.v_proj.weight": "pytorch_model-00037-of-00050.bin", + "model.layers.104.input_layernorm.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.mlp.down_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.mlp.gate_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.mlp.up_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.post_attention_layernorm.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.self_attn.k_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.self_attn.o_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.self_attn.q_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.104.self_attn.v_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.input_layernorm.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.mlp.down_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.mlp.gate_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.mlp.up_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.post_attention_layernorm.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.self_attn.k_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.self_attn.o_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.self_attn.q_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.105.self_attn.v_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.106.input_layernorm.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.106.mlp.down_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.106.mlp.gate_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.106.mlp.up_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.106.post_attention_layernorm.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.106.self_attn.k_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.106.self_attn.o_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.106.self_attn.q_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.106.self_attn.v_proj.weight": "pytorch_model-00038-of-00050.bin", + "model.layers.107.input_layernorm.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.mlp.down_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.mlp.gate_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.mlp.up_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.post_attention_layernorm.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.self_attn.k_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.self_attn.o_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.self_attn.q_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.107.self_attn.v_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.input_layernorm.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.mlp.down_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.mlp.gate_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.mlp.up_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.post_attention_layernorm.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.self_attn.k_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.self_attn.o_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.self_attn.q_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.108.self_attn.v_proj.weight": "pytorch_model-00039-of-00050.bin", + "model.layers.109.input_layernorm.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.mlp.down_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.mlp.gate_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.mlp.up_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.post_attention_layernorm.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.self_attn.k_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.self_attn.o_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.self_attn.q_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.109.self_attn.v_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.110.input_layernorm.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.mlp.down_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.mlp.gate_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.mlp.up_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.post_attention_layernorm.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.self_attn.k_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.self_attn.o_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.self_attn.q_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.110.self_attn.v_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.111.input_layernorm.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.111.mlp.down_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.111.mlp.gate_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.111.mlp.up_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.111.post_attention_layernorm.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.111.self_attn.k_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.111.self_attn.o_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.111.self_attn.q_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.111.self_attn.v_proj.weight": "pytorch_model-00040-of-00050.bin", + "model.layers.112.input_layernorm.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.mlp.down_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.mlp.gate_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.mlp.up_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.post_attention_layernorm.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.self_attn.k_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.self_attn.o_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.self_attn.q_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.112.self_attn.v_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.input_layernorm.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.mlp.down_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.mlp.gate_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.mlp.up_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.post_attention_layernorm.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.self_attn.k_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.self_attn.o_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.self_attn.q_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.113.self_attn.v_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.114.input_layernorm.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.114.mlp.down_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.114.mlp.gate_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.114.mlp.up_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.114.post_attention_layernorm.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.114.self_attn.k_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.114.self_attn.o_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.114.self_attn.q_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.114.self_attn.v_proj.weight": "pytorch_model-00041-of-00050.bin", + "model.layers.115.input_layernorm.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.mlp.down_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.mlp.gate_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.mlp.up_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.post_attention_layernorm.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.self_attn.k_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.self_attn.o_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.self_attn.q_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.115.self_attn.v_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.input_layernorm.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.mlp.down_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.mlp.gate_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.mlp.up_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.post_attention_layernorm.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.self_attn.k_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.self_attn.o_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.self_attn.q_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.116.self_attn.v_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.117.input_layernorm.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.117.mlp.down_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.117.mlp.gate_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.117.mlp.up_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.117.post_attention_layernorm.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.117.self_attn.k_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.117.self_attn.o_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.117.self_attn.q_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.117.self_attn.v_proj.weight": "pytorch_model-00042-of-00050.bin", + "model.layers.118.input_layernorm.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.mlp.down_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.mlp.gate_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.mlp.up_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.post_attention_layernorm.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.self_attn.k_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.self_attn.o_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.self_attn.q_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.118.self_attn.v_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.input_layernorm.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.mlp.down_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.mlp.gate_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.mlp.up_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.post_attention_layernorm.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.self_attn.k_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.self_attn.o_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.self_attn.q_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.119.self_attn.v_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.120.input_layernorm.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.120.mlp.down_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.120.mlp.gate_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.120.mlp.up_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.120.post_attention_layernorm.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.120.self_attn.k_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.120.self_attn.o_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.120.self_attn.q_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.120.self_attn.v_proj.weight": "pytorch_model-00043-of-00050.bin", + "model.layers.121.input_layernorm.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.mlp.down_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.mlp.gate_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.mlp.up_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.post_attention_layernorm.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.self_attn.k_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.self_attn.o_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.self_attn.q_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.121.self_attn.v_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.input_layernorm.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.mlp.down_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.mlp.gate_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.mlp.up_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.post_attention_layernorm.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.self_attn.k_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.self_attn.o_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.self_attn.q_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.122.self_attn.v_proj.weight": "pytorch_model-00044-of-00050.bin", + "model.layers.123.input_layernorm.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.mlp.down_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.mlp.gate_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.mlp.up_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.post_attention_layernorm.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.self_attn.k_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.self_attn.o_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.self_attn.q_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.123.self_attn.v_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.input_layernorm.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.mlp.down_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.mlp.gate_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.mlp.up_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.post_attention_layernorm.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.self_attn.k_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.self_attn.o_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.self_attn.q_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.124.self_attn.v_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.125.input_layernorm.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.125.mlp.down_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.125.mlp.gate_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.125.mlp.up_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.125.post_attention_layernorm.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.125.self_attn.k_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.125.self_attn.o_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.125.self_attn.q_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.125.self_attn.v_proj.weight": "pytorch_model-00045-of-00050.bin", + "model.layers.126.input_layernorm.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.mlp.down_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.mlp.gate_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.mlp.up_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.post_attention_layernorm.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.self_attn.k_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.self_attn.o_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.self_attn.q_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.126.self_attn.v_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.input_layernorm.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.mlp.down_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.mlp.gate_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.mlp.up_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.post_attention_layernorm.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.self_attn.k_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.self_attn.o_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.self_attn.q_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.127.self_attn.v_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.128.input_layernorm.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.128.mlp.down_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.128.mlp.gate_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.128.mlp.up_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.128.post_attention_layernorm.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.128.self_attn.k_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.128.self_attn.o_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.128.self_attn.q_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.128.self_attn.v_proj.weight": "pytorch_model-00046-of-00050.bin", + "model.layers.129.input_layernorm.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.mlp.down_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.mlp.gate_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.mlp.up_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.post_attention_layernorm.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.self_attn.k_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.self_attn.o_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.self_attn.q_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.129.self_attn.v_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00050.bin", + "model.layers.130.input_layernorm.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.mlp.down_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.mlp.gate_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.mlp.up_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.post_attention_layernorm.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.self_attn.k_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.self_attn.o_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.self_attn.q_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.130.self_attn.v_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.131.input_layernorm.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.131.mlp.down_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.131.mlp.gate_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.131.mlp.up_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.131.post_attention_layernorm.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.131.self_attn.k_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.131.self_attn.o_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.131.self_attn.q_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.131.self_attn.v_proj.weight": "pytorch_model-00047-of-00050.bin", + "model.layers.132.input_layernorm.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.mlp.down_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.mlp.gate_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.mlp.up_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.post_attention_layernorm.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.self_attn.k_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.self_attn.o_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.self_attn.q_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.132.self_attn.v_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.input_layernorm.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.mlp.down_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.mlp.gate_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.mlp.up_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.post_attention_layernorm.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.self_attn.k_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.self_attn.o_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.self_attn.q_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.133.self_attn.v_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.134.input_layernorm.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.134.mlp.down_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.134.mlp.gate_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.134.mlp.up_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.134.post_attention_layernorm.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.134.self_attn.k_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.134.self_attn.o_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.134.self_attn.q_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.134.self_attn.v_proj.weight": "pytorch_model-00048-of-00050.bin", + "model.layers.135.input_layernorm.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.mlp.down_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.mlp.gate_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.mlp.up_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.post_attention_layernorm.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.self_attn.k_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.self_attn.o_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.self_attn.q_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.135.self_attn.v_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.input_layernorm.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.mlp.down_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.mlp.gate_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.mlp.up_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.post_attention_layernorm.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.self_attn.k_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.self_attn.o_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.self_attn.q_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.136.self_attn.v_proj.weight": "pytorch_model-00049-of-00050.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00050.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00050.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00050.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00050.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00050.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00050.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00050.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00050.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00050.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00050.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.40.input_layernorm.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.mlp.down_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.mlp.up_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.41.input_layernorm.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.41.mlp.down_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.41.mlp.up_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00015-of-00050.bin", + "model.layers.42.input_layernorm.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.mlp.down_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.mlp.up_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.input_layernorm.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.mlp.down_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.mlp.up_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.44.input_layernorm.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.44.mlp.down_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.44.mlp.up_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00016-of-00050.bin", + "model.layers.45.input_layernorm.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.mlp.down_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.mlp.up_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.input_layernorm.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.mlp.down_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.mlp.up_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.47.input_layernorm.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.47.mlp.down_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.47.mlp.up_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00017-of-00050.bin", + "model.layers.48.input_layernorm.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.mlp.down_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.mlp.up_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.input_layernorm.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.mlp.down_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.mlp.up_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00050.bin", + "model.layers.50.input_layernorm.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.50.mlp.down_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.50.mlp.up_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00018-of-00050.bin", + "model.layers.51.input_layernorm.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.mlp.down_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.mlp.up_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.input_layernorm.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.mlp.down_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.mlp.up_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00019-of-00050.bin", + "model.layers.53.input_layernorm.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.mlp.down_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.mlp.up_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.input_layernorm.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.mlp.down_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.mlp.up_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.55.input_layernorm.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.55.mlp.down_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.55.mlp.up_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00020-of-00050.bin", + "model.layers.56.input_layernorm.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.mlp.down_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.mlp.up_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.input_layernorm.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.mlp.down_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.mlp.up_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.58.input_layernorm.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.58.mlp.down_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.58.mlp.up_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00021-of-00050.bin", + "model.layers.59.input_layernorm.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.mlp.down_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.mlp.up_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.60.input_layernorm.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.mlp.down_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.mlp.up_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.61.input_layernorm.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.61.mlp.down_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.61.mlp.up_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00022-of-00050.bin", + "model.layers.62.input_layernorm.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.mlp.down_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.mlp.up_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.input_layernorm.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.mlp.down_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.mlp.up_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.64.input_layernorm.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.64.mlp.down_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.64.mlp.up_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00023-of-00050.bin", + "model.layers.65.input_layernorm.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.mlp.down_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.mlp.up_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.input_layernorm.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.mlp.down_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.mlp.up_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00024-of-00050.bin", + "model.layers.67.input_layernorm.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.mlp.down_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.mlp.up_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.input_layernorm.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.mlp.down_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.mlp.up_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.69.input_layernorm.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.69.mlp.down_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.69.mlp.up_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00025-of-00050.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.70.input_layernorm.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.mlp.down_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.mlp.up_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.input_layernorm.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.mlp.down_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.mlp.up_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.72.input_layernorm.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.72.mlp.down_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.72.mlp.up_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00026-of-00050.bin", + "model.layers.73.input_layernorm.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.mlp.down_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.mlp.up_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.input_layernorm.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.mlp.down_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.mlp.up_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.75.input_layernorm.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.75.mlp.down_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.75.mlp.up_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00027-of-00050.bin", + "model.layers.76.input_layernorm.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.mlp.down_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.mlp.up_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.input_layernorm.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.mlp.down_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.mlp.up_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.78.input_layernorm.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.78.mlp.down_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.78.mlp.up_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00028-of-00050.bin", + "model.layers.79.input_layernorm.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.mlp.down_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.mlp.up_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00050.bin", + "model.layers.80.input_layernorm.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.mlp.down_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.mlp.gate_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.mlp.up_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.post_attention_layernorm.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.self_attn.k_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.self_attn.o_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.self_attn.q_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.80.self_attn.v_proj.weight": "pytorch_model-00029-of-00050.bin", + "model.layers.81.input_layernorm.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.mlp.down_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.mlp.gate_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.mlp.up_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.post_attention_layernorm.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.self_attn.k_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.self_attn.o_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.self_attn.q_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.81.self_attn.v_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.input_layernorm.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.mlp.down_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.mlp.gate_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.mlp.up_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.post_attention_layernorm.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.self_attn.k_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.self_attn.o_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.self_attn.q_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.82.self_attn.v_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.83.input_layernorm.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.83.mlp.down_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.83.mlp.gate_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.83.mlp.up_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.83.post_attention_layernorm.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.83.self_attn.k_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.83.self_attn.o_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.83.self_attn.q_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.83.self_attn.v_proj.weight": "pytorch_model-00030-of-00050.bin", + "model.layers.84.input_layernorm.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.mlp.down_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.mlp.gate_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.mlp.up_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.post_attention_layernorm.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.self_attn.k_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.self_attn.o_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.self_attn.q_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.84.self_attn.v_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.input_layernorm.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.mlp.down_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.mlp.gate_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.mlp.up_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.post_attention_layernorm.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.self_attn.k_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.self_attn.o_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.self_attn.q_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.85.self_attn.v_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.86.input_layernorm.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.86.mlp.down_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.86.mlp.gate_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.86.mlp.up_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.86.post_attention_layernorm.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.86.self_attn.k_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.86.self_attn.o_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.86.self_attn.q_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.86.self_attn.v_proj.weight": "pytorch_model-00031-of-00050.bin", + "model.layers.87.input_layernorm.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.mlp.down_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.mlp.gate_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.mlp.up_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.post_attention_layernorm.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.self_attn.k_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.self_attn.o_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.self_attn.q_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.87.self_attn.v_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.input_layernorm.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.mlp.down_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.mlp.gate_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.mlp.up_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.post_attention_layernorm.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.self_attn.k_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.self_attn.o_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.self_attn.q_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.88.self_attn.v_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.89.input_layernorm.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.89.mlp.down_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.89.mlp.gate_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.89.mlp.up_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.89.post_attention_layernorm.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.89.self_attn.k_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.89.self_attn.o_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.89.self_attn.q_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.89.self_attn.v_proj.weight": "pytorch_model-00032-of-00050.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00050.bin", + "model.layers.90.input_layernorm.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.mlp.down_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.mlp.gate_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.mlp.up_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.post_attention_layernorm.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.self_attn.k_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.self_attn.o_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.self_attn.q_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.90.self_attn.v_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.input_layernorm.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.mlp.down_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.mlp.gate_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.mlp.up_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.post_attention_layernorm.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.self_attn.k_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.self_attn.o_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.self_attn.q_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.91.self_attn.v_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.92.input_layernorm.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.92.mlp.down_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.92.mlp.gate_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.92.mlp.up_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.92.post_attention_layernorm.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.92.self_attn.k_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.92.self_attn.o_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.92.self_attn.q_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.92.self_attn.v_proj.weight": "pytorch_model-00033-of-00050.bin", + "model.layers.93.input_layernorm.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.mlp.down_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.mlp.gate_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.mlp.up_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.post_attention_layernorm.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.self_attn.k_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.self_attn.o_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.self_attn.q_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.93.self_attn.v_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.input_layernorm.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.mlp.down_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.mlp.gate_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.mlp.up_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.post_attention_layernorm.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.self_attn.k_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.self_attn.o_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.self_attn.q_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.94.self_attn.v_proj.weight": "pytorch_model-00034-of-00050.bin", + "model.layers.95.input_layernorm.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.mlp.down_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.mlp.gate_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.mlp.up_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.post_attention_layernorm.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.self_attn.k_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.self_attn.o_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.self_attn.q_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.95.self_attn.v_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.input_layernorm.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.mlp.down_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.mlp.gate_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.mlp.up_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.post_attention_layernorm.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.self_attn.k_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.self_attn.o_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.self_attn.q_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.96.self_attn.v_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.97.input_layernorm.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.97.mlp.down_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.97.mlp.gate_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.97.mlp.up_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.97.post_attention_layernorm.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.97.self_attn.k_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.97.self_attn.o_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.97.self_attn.q_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.97.self_attn.v_proj.weight": "pytorch_model-00035-of-00050.bin", + "model.layers.98.input_layernorm.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.mlp.down_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.mlp.gate_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.mlp.up_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.post_attention_layernorm.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.self_attn.k_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.self_attn.o_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.self_attn.q_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.98.self_attn.v_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.input_layernorm.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.mlp.down_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.mlp.gate_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.mlp.up_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.post_attention_layernorm.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.self_attn.k_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.self_attn.o_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.self_attn.q_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.layers.99.self_attn.v_proj.weight": "pytorch_model-00036-of-00050.bin", + "model.norm.weight": "pytorch_model-00049-of-00050.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..ec01507107f07ae76fbe14426961c9b380b6d4e7 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,29 @@ +{ + "additional_special_tokens": [ + "", + "", + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5da7cdebc2203daf955e3e6ad61e303a41601ef3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,72 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32001": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32002": { + "content": "<|model|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "", + "" + ], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": "", + "use_default_system_prompt": true, + "use_fast": true +}