Upload with huggingface_hub

llama-13b/config.json

@@ -0,0 +1 @@
+{"architectures": ["LLaMAForCausalLM"], "bos_token_id": 0, "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 5120, "intermediate_size": 13824, "initializer_range": 0.02, "max_sequence_length": 2048, "model_type": "llama", "num_attention_heads": 40, "num_hidden_layers": 40, "pad_token_id": -1, "rms_norm_eps": 1e-06, "torch_dtype": "float16", "transformers_version": "4.27.0.dev0", "use_cache": true, "vocab_size": 32000}

llama-13b/generation_config.json

@@ -0,0 +1 @@
+{"_from_model_config": true, "bos_token_id": 0, "eos_token_id": 1, "pad_token_id": -1, "transformers_version": "4.27.0.dev0"}

llama-13b/pytorch_model-00000-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0acf7fb9907cdd089474505c2f4fee1ed172ad1cbe63733a1e7d60c9bf1eb747
+size 951606497

llama-13b/pytorch_model-00001-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67caa11e3573dd1e0fcc4ebcd83b6d94666bbb172ee041373c83622b0ee1b4c
+size 951606497

llama-13b/pytorch_model-00002-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1baccbd42845b5ac0f34c0d609608235e1639da901d72c92d542845602a5db0
+size 951606497

llama-13b/pytorch_model-00003-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceff2f80ca3cd2de89e691a952fe70b12fbab400ed92a495cabfc7d0c0a524b4
+size 951606497

llama-13b/pytorch_model-00004-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac70f1647ee57e5079d56ad98754204ebe7c3b7a1936f2adfc52a4cdf73798ec
+size 951606497

llama-13b/pytorch_model-00005-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdecd8acddd5203c3780ec4778bde974639a6fae155150aae33ebe0ba3199130
+size 951606497

llama-13b/pytorch_model-00006-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280003d57045ed2e26e3ac00200a6dac5b50516c6449f37fe7bcb735fecf0215
+size 951606497

llama-13b/pytorch_model-00007-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b084fc411e02f1ace062bde6c474b94ac6a2ee412edf9991fe128d631197002
+size 951606497

llama-13b/pytorch_model-00008-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f726ca7c129d3c7ba84c7b6d96ca805014ea523c1c451caa9c98eebea0d6a1
+size 951606497

llama-13b/pytorch_model-00009-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55d1d64b6b0d7701fb0ef64166d3e7f4d2e3a76aaded6543857dbf374a5a4ca
+size 951606497

llama-13b/pytorch_model-00010-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e7073f7533f3705e9ad1e591c9f3cdf788a4d42395b8e4693b0d64df90e26
+size 951606497

llama-13b/pytorch_model-00011-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89aa50a6c3515a5327ba7e4219a36f46a90e90e8b309f919320a178c8a02a30
+size 951606497

llama-13b/pytorch_model-00012-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4a23c74d518c892a490a818f6775c188862ed76eeb543974f288128e3101ea
+size 951606497

llama-13b/pytorch_model-00013-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb1f1b9fcc83302e5d2306ede5efaa1c99fdcb5a1ed15ba729e3e52fa01bf2b
+size 951606497

llama-13b/pytorch_model-00014-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ad3152a94a8ffaf46524f2d39a11ccfae89d2bd88c27924528235b5ab31895
+size 951606497

llama-13b/pytorch_model-00015-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c0318c83b334beca654277d4b5942762a49e196978201020330367675278a2
+size 951606497

llama-13b/pytorch_model-00016-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5fae4d1641458260da83c1f30a15d567d6d9257a17d37bf09d7d1e66ad1392
+size 951606497

llama-13b/pytorch_model-00017-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0402a782b67513e5f1aabb8bcf682e42ca4d25d0252f6ad8a3f3525b60a764a
+size 951606497

llama-13b/pytorch_model-00018-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbfea4bd9dfd509cdccf359547eb5c65965a2df725418ecd1f14d42fcacbd8f7
+size 951606497

llama-13b/pytorch_model-00019-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223905ece36ca066e86da5ed79ea3e6152c46015d4e4fa9dd497d78d0d18850e
+size 951606497

llama-13b/pytorch_model-00020-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1ca2ba04e0b95641af41e8e3b7aa4104ce8688aa395620e89437f0ec2b60e9
+size 951606497

llama-13b/pytorch_model-00021-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51ca262b1e359dc4a6d12d83cc77dbf0046aec9df29d5f96ae1dc0469439e15
+size 951606497

llama-13b/pytorch_model-00022-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ad4b55deb49618af12e174e8c3da0e048ba8b83be0b7f4e4536a75fe188b15
+size 951606497

llama-13b/pytorch_model-00023-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42ac3c66507577a42392a579e1e0037533d42f6c59b515fd430042e185b4f9b
+size 951606497

llama-13b/pytorch_model-00024-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95493c4814125456a1c337b2bc63818c78df49f2eed749a5dd6ed63940c78b16
+size 951606497

llama-13b/pytorch_model-00025-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06b6fa62661aa6a17a720dbc9dd51b93c508c520c313ea76b97abf5874fe809
+size 951606497

llama-13b/pytorch_model-00026-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6824e9726db3f7eabcc2ceee6e01ccd8ef3858a0630a1c3e1965be3a1514454a
+size 951606497

llama-13b/pytorch_model-00027-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b191fdf5d43e946242b3b81370956afa22fcb11491f329a6aa5fa086534219
+size 951606497

llama-13b/pytorch_model-00028-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aec63cc56e386ddddff23937d2a19af618bbfc7f93be1d7bb1fedc53efeea65
+size 951606497

llama-13b/pytorch_model-00029-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3fb6740d1352bd23d687341f50e756d2618953c96d3e436188e58173d7d05e
+size 951606497

llama-13b/pytorch_model-00030-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af018772383036d16b554ab960592aeb6f7bb84a568003f5bd742391930d856c
+size 951606497

llama-13b/pytorch_model-00031-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e19b2d91960f1c135b63748a20040cfdba19ed6b316d130bf3ce16b9fc10b9b
+size 951606497

llama-13b/pytorch_model-00032-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba31be5fa28e26a3022d89d6d53f4a4cdfcf89c75d178e8cb9e61fcc69ad9086
+size 951606497

llama-13b/pytorch_model-00033-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bd042688d2b4f34060ffe5fcfbbab811d6030b0a729493b703ad6b0a68151f
+size 951606497

llama-13b/pytorch_model-00034-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad173d4e905b9e828d6a2e897462d322317c07550d0c8121426e652d874e0b5
+size 951606497

llama-13b/pytorch_model-00035-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dc2d6e0abe0d701a4453e9377065b6dd38220fd8973bfc9c415cbafb9755df
+size 951606497

llama-13b/pytorch_model-00036-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9968131f38447afb6d05da5d5572ceb1cde4677b77829e02e26a0b136bfbc666
+size 951606497

llama-13b/pytorch_model-00037-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d215cacc0c9eb3a70759a931f274e5a0ea8ad0afdd65788bf8a12f7a821632
+size 951606497

llama-13b/pytorch_model-00038-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f37fe2f4a24a5446f3b92bfbb13538dd47cbf549f6f6e705a5dcd681928e95
+size 951606497

llama-13b/pytorch_model-00039-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe5faa754faddbafded0f41757b29bb3073bb910389842cfbf16e715f9482bb
+size 951606497

llama-13b/pytorch_model-00040-of-00041.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5655a67609e1e897145ed297ee0a7a57856d35969aff8032664ceaa1747e9b0
+size 983051788

llama-13b/pytorch_model.bin.index.json

@@ -0,0 +1 @@
+{"weight_map": {"model.decoder.layers.0.attention_norm.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.ffn_norm.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.self_attn.o_proj.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.feed_forward.w1.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.feed_forward.w2.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.0.feed_forward.w3.weight": "pytorch_model-00000-of-00041.bin", "model.decoder.layers.1.attention_norm.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.ffn_norm.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.feed_forward.w1.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.feed_forward.w2.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.1.feed_forward.w3.weight": "pytorch_model-00001-of-00041.bin", "model.decoder.layers.2.attention_norm.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.ffn_norm.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.feed_forward.w1.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.feed_forward.w2.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.2.feed_forward.w3.weight": "pytorch_model-00002-of-00041.bin", "model.decoder.layers.3.attention_norm.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.ffn_norm.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.feed_forward.w1.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.feed_forward.w2.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.3.feed_forward.w3.weight": "pytorch_model-00003-of-00041.bin", "model.decoder.layers.4.attention_norm.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.ffn_norm.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.feed_forward.w1.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.feed_forward.w2.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.4.feed_forward.w3.weight": "pytorch_model-00004-of-00041.bin", "model.decoder.layers.5.attention_norm.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.ffn_norm.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.feed_forward.w1.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.feed_forward.w2.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.5.feed_forward.w3.weight": "pytorch_model-00005-of-00041.bin", "model.decoder.layers.6.attention_norm.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.ffn_norm.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.self_attn.o_proj.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.feed_forward.w1.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.feed_forward.w2.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.6.feed_forward.w3.weight": "pytorch_model-00006-of-00041.bin", "model.decoder.layers.7.attention_norm.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.ffn_norm.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.self_attn.o_proj.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.feed_forward.w1.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.feed_forward.w2.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.7.feed_forward.w3.weight": "pytorch_model-00007-of-00041.bin", "model.decoder.layers.8.attention_norm.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.ffn_norm.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.self_attn.o_proj.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.feed_forward.w1.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.feed_forward.w2.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.8.feed_forward.w3.weight": "pytorch_model-00008-of-00041.bin", "model.decoder.layers.9.attention_norm.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.ffn_norm.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.self_attn.o_proj.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.feed_forward.w1.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.feed_forward.w2.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.9.feed_forward.w3.weight": "pytorch_model-00009-of-00041.bin", "model.decoder.layers.10.attention_norm.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.ffn_norm.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.self_attn.o_proj.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.feed_forward.w1.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.feed_forward.w2.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.10.feed_forward.w3.weight": "pytorch_model-00010-of-00041.bin", "model.decoder.layers.11.attention_norm.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.ffn_norm.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.self_attn.o_proj.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.feed_forward.w1.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.feed_forward.w2.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.11.feed_forward.w3.weight": "pytorch_model-00011-of-00041.bin", "model.decoder.layers.12.attention_norm.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.ffn_norm.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.self_attn.o_proj.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.feed_forward.w1.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.feed_forward.w2.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.12.feed_forward.w3.weight": "pytorch_model-00012-of-00041.bin", "model.decoder.layers.13.attention_norm.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.ffn_norm.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.self_attn.o_proj.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.feed_forward.w1.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.feed_forward.w2.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.13.feed_forward.w3.weight": "pytorch_model-00013-of-00041.bin", "model.decoder.layers.14.attention_norm.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.ffn_norm.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.self_attn.o_proj.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.feed_forward.w1.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.feed_forward.w2.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.14.feed_forward.w3.weight": "pytorch_model-00014-of-00041.bin", "model.decoder.layers.15.attention_norm.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.ffn_norm.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.self_attn.o_proj.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.feed_forward.w1.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.feed_forward.w2.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.15.feed_forward.w3.weight": "pytorch_model-00015-of-00041.bin", "model.decoder.layers.16.attention_norm.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.ffn_norm.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.self_attn.o_proj.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.feed_forward.w1.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.feed_forward.w2.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.16.feed_forward.w3.weight": "pytorch_model-00016-of-00041.bin", "model.decoder.layers.17.attention_norm.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.ffn_norm.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.self_attn.o_proj.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.feed_forward.w1.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.feed_forward.w2.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.17.feed_forward.w3.weight": "pytorch_model-00017-of-00041.bin", "model.decoder.layers.18.attention_norm.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.ffn_norm.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.self_attn.o_proj.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.feed_forward.w1.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.feed_forward.w2.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.18.feed_forward.w3.weight": "pytorch_model-00018-of-00041.bin", "model.decoder.layers.19.attention_norm.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.ffn_norm.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.self_attn.o_proj.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.feed_forward.w1.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.feed_forward.w2.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.19.feed_forward.w3.weight": "pytorch_model-00019-of-00041.bin", "model.decoder.layers.20.attention_norm.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.ffn_norm.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.self_attn.o_proj.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.feed_forward.w1.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.feed_forward.w2.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.20.feed_forward.w3.weight": "pytorch_model-00020-of-00041.bin", "model.decoder.layers.21.attention_norm.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.ffn_norm.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.self_attn.o_proj.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.feed_forward.w1.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.feed_forward.w2.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.21.feed_forward.w3.weight": "pytorch_model-00021-of-00041.bin", "model.decoder.layers.22.attention_norm.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.ffn_norm.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.self_attn.o_proj.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.feed_forward.w1.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.feed_forward.w2.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.22.feed_forward.w3.weight": "pytorch_model-00022-of-00041.bin", "model.decoder.layers.23.attention_norm.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.ffn_norm.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.self_attn.o_proj.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.feed_forward.w1.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.feed_forward.w2.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.23.feed_forward.w3.weight": "pytorch_model-00023-of-00041.bin", "model.decoder.layers.24.attention_norm.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.ffn_norm.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.self_attn.o_proj.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.feed_forward.w1.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.feed_forward.w2.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.24.feed_forward.w3.weight": "pytorch_model-00024-of-00041.bin", "model.decoder.layers.25.attention_norm.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.ffn_norm.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.self_attn.o_proj.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.feed_forward.w1.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.feed_forward.w2.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.25.feed_forward.w3.weight": "pytorch_model-00025-of-00041.bin", "model.decoder.layers.26.attention_norm.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.ffn_norm.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.self_attn.o_proj.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.feed_forward.w1.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.feed_forward.w2.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.26.feed_forward.w3.weight": "pytorch_model-00026-of-00041.bin", "model.decoder.layers.27.attention_norm.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.ffn_norm.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.self_attn.o_proj.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.feed_forward.w1.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.feed_forward.w2.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.27.feed_forward.w3.weight": "pytorch_model-00027-of-00041.bin", "model.decoder.layers.28.attention_norm.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.ffn_norm.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.self_attn.o_proj.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.feed_forward.w1.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.feed_forward.w2.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.28.feed_forward.w3.weight": "pytorch_model-00028-of-00041.bin", "model.decoder.layers.29.attention_norm.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.ffn_norm.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.self_attn.o_proj.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.feed_forward.w1.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.feed_forward.w2.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.29.feed_forward.w3.weight": "pytorch_model-00029-of-00041.bin", "model.decoder.layers.30.attention_norm.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.ffn_norm.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.self_attn.o_proj.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.feed_forward.w1.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.feed_forward.w2.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.30.feed_forward.w3.weight": "pytorch_model-00030-of-00041.bin", "model.decoder.layers.31.attention_norm.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.ffn_norm.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.self_attn.o_proj.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.feed_forward.w1.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.feed_forward.w2.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.31.feed_forward.w3.weight": "pytorch_model-00031-of-00041.bin", "model.decoder.layers.32.attention_norm.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.ffn_norm.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.self_attn.q_proj.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.self_attn.k_proj.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.self_attn.v_proj.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.self_attn.o_proj.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.feed_forward.w1.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.feed_forward.w2.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.32.feed_forward.w3.weight": "pytorch_model-00032-of-00041.bin", "model.decoder.layers.33.attention_norm.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.ffn_norm.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.self_attn.q_proj.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.self_attn.k_proj.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.self_attn.v_proj.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.self_attn.o_proj.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.feed_forward.w1.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.feed_forward.w2.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.33.feed_forward.w3.weight": "pytorch_model-00033-of-00041.bin", "model.decoder.layers.34.attention_norm.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.ffn_norm.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.self_attn.q_proj.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.self_attn.k_proj.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.self_attn.v_proj.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.self_attn.o_proj.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.feed_forward.w1.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.feed_forward.w2.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.34.feed_forward.w3.weight": "pytorch_model-00034-of-00041.bin", "model.decoder.layers.35.attention_norm.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.ffn_norm.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.self_attn.q_proj.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.self_attn.k_proj.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.self_attn.v_proj.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.self_attn.o_proj.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.feed_forward.w1.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.feed_forward.w2.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.35.feed_forward.w3.weight": "pytorch_model-00035-of-00041.bin", "model.decoder.layers.36.attention_norm.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.ffn_norm.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.self_attn.q_proj.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.self_attn.k_proj.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.self_attn.v_proj.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.self_attn.o_proj.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.feed_forward.w1.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.feed_forward.w2.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.36.feed_forward.w3.weight": "pytorch_model-00036-of-00041.bin", "model.decoder.layers.37.attention_norm.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.ffn_norm.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.self_attn.q_proj.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.self_attn.k_proj.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.self_attn.v_proj.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.self_attn.o_proj.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.feed_forward.w1.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.feed_forward.w2.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.37.feed_forward.w3.weight": "pytorch_model-00037-of-00041.bin", "model.decoder.layers.38.attention_norm.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.ffn_norm.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.self_attn.q_proj.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.self_attn.k_proj.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.self_attn.v_proj.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.self_attn.o_proj.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.feed_forward.w1.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.feed_forward.w2.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.38.feed_forward.w3.weight": "pytorch_model-00038-of-00041.bin", "model.decoder.layers.39.attention_norm.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.ffn_norm.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.self_attn.q_proj.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.self_attn.k_proj.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.self_attn.v_proj.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.self_attn.o_proj.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.feed_forward.w1.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.feed_forward.w2.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.layers.39.feed_forward.w3.weight": "pytorch_model-00039-of-00041.bin", "model.decoder.norm.weight": "pytorch_model-00040-of-00041.bin", "model.decoder.embed_tokens.weight": "pytorch_model-00040-of-00041.bin", "lm_head.weight": "pytorch_model-00040-of-00041.bin"}, "metadata": {"total_size": 26031728640}}

llama-13b/special_tokens_map.json

@@ -0,0 +1 @@
+{}

llama-13b/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

llama-13b/tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""}

tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""}