diff --git a/config.json b/config.json index e5170ad338ed0bf71dad0789ccdf5d95bb1f700a..1886e4e3e8eb8c8b22f0df74b6edfb1871410d1c 100644 --- a/config.json +++ b/config.json @@ -16,7 +16,7 @@ "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "float16", - "transformers_version": "4.30.0", + "transformers_version": "4.28.0.dev0", "use_cache": true, "vocab_size": 52000 } diff --git a/generation_config.json b/generation_config.json index fd6e96ff926b1a3949f73cbf9af21dca59302464..e0e4de86ce8b3976fd244ec4938fbf3936d388df 100644 --- a/generation_config.json +++ b/generation_config.json @@ -3,5 +3,5 @@ "bos_token_id": 1, "eos_token_id": 0, "pad_token_id": 0, - "transformers_version": "4.30.0" + "transformers_version": "4.28.0.dev0" } diff --git a/model-00001-of-00028.safetensors b/model-00001-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..053d2bf71b5304a20f510ccecc46f9a4c03cb7cf --- /dev/null +++ b/model-00001-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29912762ced57be1cd94520a508b4e558ddc89428229911f4bfdf3d3fd9d84a3 +size 883754024 diff --git a/model-00002-of-00028.safetensors b/model-00002-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc0389eb76d3e4d32b3d5bca4056b8a7a6306c54 --- /dev/null +++ b/model-00002-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a1e380fbdd663b9103f64d93f2822e831d9f65699d52ecdff31cf0bb5d8377 +size 969975720 diff --git a/model-00003-of-00028.safetensors b/model-00003-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f66a2df308d77d8a54df31759fbd408b23077f18 --- /dev/null +++ b/model-00003-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b950cc4292324494598074e277f95c73d81a5220d696fb00751d9ab123fb63e +size 933255328 diff --git a/model-00004-of-00028.safetensors b/model-00004-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba3a796d79607679eaed715de1c0b306990dab83 --- /dev/null +++ b/model-00004-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ba7f03dd01cef8c6e2057624c93b6c6f61f86686402a02c83a1e60d4c205fa +size 969975720 diff --git a/model-00005-of-00028.safetensors b/model-00005-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..66ab2dcc1e7280a3c82ec76583a9c690b71ff34f --- /dev/null +++ b/model-00005-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a430a3f6b68ca4756e40bf93ee10137a7b233bb8bead624b748d762bd8249a84 +size 933255328 diff --git a/model-00006-of-00028.safetensors b/model-00006-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..714c474e8d1949e49a91c211c2dc3e1e98dd5761 --- /dev/null +++ b/model-00006-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18eae0463af72bd26b948311363edf733b4a28732c10e564d24c0f3f8d6c1a3a +size 969975720 diff --git a/model-00007-of-00028.safetensors b/model-00007-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e10fada713ac29249aa38664f76cc2196bbac13 --- /dev/null +++ b/model-00007-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd326f182800d954ea04ec7ce2c0a7a24767eb9e008b4eb855de7eed9e6e8f9 +size 933255328 diff --git a/model-00008-of-00028.safetensors b/model-00008-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06288907b746d23fad3ecc98e60e6304b21d80ac --- /dev/null +++ b/model-00008-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d97007d2ad725fe9ef865b7c8374909625d82667058a8a264af8dd3d3a3f34 +size 969975728 diff --git a/model-00009-of-00028.safetensors b/model-00009-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ebfc8d1cde552ce362063f4fde0f4a07df24e63 --- /dev/null +++ b/model-00009-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e7f8e7672e4b6f49eefaf77fec35df719ec4a5802a8c1d4276b330681d7290 +size 933255344 diff --git a/model-00010-of-00028.safetensors b/model-00010-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c51d55131e0ba6d2abbe71a0ab379c11fae7ed3e --- /dev/null +++ b/model-00010-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3689c4534e6c3523743a6e57af4502074c189eed6623472dc14952fa6aad37db +size 969975736 diff --git a/model-00011-of-00028.safetensors b/model-00011-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..979cdc6d2d05dc95bb98034506af885c27b1f0aa --- /dev/null +++ b/model-00011-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f8f2fd4658c684b07f70d56088208ee4deff34f1183e03d4e42b92a0b7e554 +size 933255344 diff --git a/model-00012-of-00028.safetensors b/model-00012-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ccd411ad6306a8307576e1a80125b5b0070c0ac1 --- /dev/null +++ b/model-00012-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee95a5e98b7b4c6e66b03db737b7fd85da1cfc1a00bbd538e39d11c8db934f6 +size 969975736 diff --git a/model-00013-of-00028.safetensors b/model-00013-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..81af4829f326bbe73b5acf1b6ebb10000ecf5d36 --- /dev/null +++ b/model-00013-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9996ed42ea245dbab2e0ef086f11d18ebdff9b412e433f1d7bba0368bb759269 +size 933255344 diff --git a/model-00014-of-00028.safetensors b/model-00014-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7bf3488c2efea3ba0cf9ccfc63304b1f2c6437b --- /dev/null +++ b/model-00014-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321022996d2a18e0763c042f60c199b047d989cde2dcd67d0d2fbb68df9856fc +size 969975736 diff --git a/model-00015-of-00028.safetensors b/model-00015-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e81cb53f2073401decf09c5f46ac7877a698b9c --- /dev/null +++ b/model-00015-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649781dcd3c63e1879e7d9c35b1a87b05c4c1b6997fab224c2cac281e0e242a0 +size 933255344 diff --git a/model-00016-of-00028.safetensors b/model-00016-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc024cec56d86c9272ab256820869b0245f32b88 --- /dev/null +++ b/model-00016-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184dcabf1f2cc50583cdbc66b4b81b241ae62deeff4e5e5b7e078e1719867c9a +size 969975736 diff --git a/model-00017-of-00028.safetensors b/model-00017-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26b0f84f7b9ec1a6d2d478b4dd5fa52ea13504dc --- /dev/null +++ b/model-00017-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988b2b18c0c0afa608bc5a3e139326482e786218572351fd456281b7afd25b1c +size 933255344 diff --git a/model-00018-of-00028.safetensors b/model-00018-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87d5208d4493d8f5ce84e8d76016b4e8be4685bf --- /dev/null +++ b/model-00018-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704f5490455b66b1b44202d0a0f7066c8fe56b9d9f80740ca8ec2da6b160a55a +size 969975736 diff --git a/model-00019-of-00028.safetensors b/model-00019-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d73dd290d4ac804e895f1c8371677fc83c148ec8 --- /dev/null +++ b/model-00019-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d85ea989eb7e2ce7f5d373b7248fb7e55c6780e44d9a3cd04a322de9038a186 +size 933255344 diff --git a/model-00020-of-00028.safetensors b/model-00020-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f169a76979651330dfca8573e16c34a87d89b88d --- /dev/null +++ b/model-00020-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b0861f77ad745ec6ebcc3834ef862dd7de526591ef9463c7c1df6c3922fe7a +size 969975736 diff --git a/model-00021-of-00028.safetensors b/model-00021-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99d4ed1c2d2832c3b1f69a8dc67305ffe7f54767 --- /dev/null +++ b/model-00021-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab0f6556424ca995db043de2372562c969ca055b9d44967c931cf469494093d +size 933255344 diff --git a/model-00022-of-00028.safetensors b/model-00022-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0dff7e9502a52703baa2ad43cd7e4bf67c6afa5 --- /dev/null +++ b/model-00022-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e42f4978cf3f113b229dee2c38ac80b4073e05008b0b1e4c0239ec59f53549 +size 969975736 diff --git a/model-00023-of-00028.safetensors b/model-00023-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aeb3bd0f60493d965bcb904e312c680087660756 --- /dev/null +++ b/model-00023-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301fe277844c725cfc04664d4354895e8c004e60874409e5d50b85e1923c3db0 +size 933255344 diff --git a/model-00024-of-00028.safetensors b/model-00024-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50e0d9e70adb6af663e4d2bb7ee9c575c44b3667 --- /dev/null +++ b/model-00024-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac89771a8b714312c481788a2b8a04099d8e44d95829dd1d71eb95c3be54eca +size 969975736 diff --git a/model-00025-of-00028.safetensors b/model-00025-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f04c35e0c7f59c5b099ed0f2509bb113cc55cd5 --- /dev/null +++ b/model-00025-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0973973b16a934b88ae75777963619cad81224d35b05fecbd19f90f543d8f65 +size 933255344 diff --git a/model-00026-of-00028.safetensors b/model-00026-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..870eaa0301082b502c36f03fff30b33b84aee85f --- /dev/null +++ b/model-00026-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d085d4c8415c98efe47d57ddf8b9ea892f9a70f6e06ecf7f1ad3d34050cb4e3b +size 969975736 diff --git a/model-00027-of-00028.safetensors b/model-00027-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a78e43d2bc21070c118c01af8d0b820f9cb5fcb --- /dev/null +++ b/model-00027-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb81571ccfbc70d8c99f3330bc9295956b450f750467c7889ceef286959e775 +size 933255344 diff --git a/model-00028-of-00028.safetensors b/model-00028-of-00028.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad254a7d78062f090588edadacf5400ddc1520a2 --- /dev/null +++ b/model-00028-of-00028.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af40a9d84101d8ce0452e46ae05ab6b5d9cea00e0f6e3d2711b89d241ac824e +size 815626904 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..badb2445912c653bc5b6aae8b17b33556d9c496d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 26441338880 + }, + "weight_map": { + "lm_head.weight": "model-00028-of-00028.safetensors", + "model.embed_tokens.weight": "model-00001-of-00028.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00028.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors", + "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00028.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00002-of-00028.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.10.input_layernorm.weight": "model-00008-of-00028.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00008-of-00028.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.11.input_layernorm.weight": "model-00009-of-00028.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00009-of-00028.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.12.input_layernorm.weight": "model-00010-of-00028.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00009-of-00028.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", + "model.layers.13.input_layernorm.weight": "model-00010-of-00028.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00010-of-00028.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.14.input_layernorm.weight": "model-00011-of-00028.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", + "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00011-of-00028.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.15.input_layernorm.weight": "model-00012-of-00028.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00011-of-00028.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", + "model.layers.16.input_layernorm.weight": "model-00012-of-00028.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00012-of-00028.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.17.input_layernorm.weight": "model-00013-of-00028.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", + "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00013-of-00028.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.18.input_layernorm.weight": "model-00014-of-00028.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00013-of-00028.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", + "model.layers.19.input_layernorm.weight": "model-00014-of-00028.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00014-of-00028.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00028.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", + "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00003-of-00028.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.20.input_layernorm.weight": "model-00015-of-00028.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", + "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00015-of-00028.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.21.input_layernorm.weight": "model-00016-of-00028.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00015-of-00028.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", + "model.layers.22.input_layernorm.weight": "model-00016-of-00028.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00016-of-00028.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.23.input_layernorm.weight": "model-00017-of-00028.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", + "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00017-of-00028.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.24.input_layernorm.weight": "model-00018-of-00028.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00017-of-00028.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", + "model.layers.25.input_layernorm.weight": "model-00018-of-00028.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00018-of-00028.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.26.input_layernorm.weight": "model-00019-of-00028.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", + "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00019-of-00028.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.27.input_layernorm.weight": "model-00020-of-00028.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00019-of-00028.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", + "model.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00020-of-00028.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.29.input_layernorm.weight": "model-00021-of-00028.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", + "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00021-of-00028.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00028.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00003-of-00028.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", + "model.layers.30.input_layernorm.weight": "model-00022-of-00028.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00021-of-00028.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", + "model.layers.31.input_layernorm.weight": "model-00022-of-00028.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00022-of-00028.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.32.input_layernorm.weight": "model-00023-of-00028.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", + "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00023-of-00028.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.33.input_layernorm.weight": "model-00024-of-00028.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00023-of-00028.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", + "model.layers.34.input_layernorm.weight": "model-00024-of-00028.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00024-of-00028.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.35.input_layernorm.weight": "model-00025-of-00028.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", + "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00025-of-00028.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.36.input_layernorm.weight": "model-00026-of-00028.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00025-of-00028.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", + "model.layers.37.input_layernorm.weight": "model-00026-of-00028.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00026-of-00028.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.38.input_layernorm.weight": "model-00027-of-00028.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", + "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00027-of-00028.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.39.input_layernorm.weight": "model-00028-of-00028.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00028-of-00028.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00028-of-00028.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00027-of-00028.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", + "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00004-of-00028.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00028.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", + "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00005-of-00028.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.6.input_layernorm.weight": "model-00006-of-00028.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00005-of-00028.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", + "model.layers.7.input_layernorm.weight": "model-00006-of-00028.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00006-of-00028.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.8.input_layernorm.weight": "model-00007-of-00028.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", + "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00007-of-00028.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.9.input_layernorm.weight": "model-00008-of-00028.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00008-of-00028.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", + "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00007-of-00028.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", + "model.norm.weight": "model-00028-of-00028.safetensors" + } +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin deleted file mode 100644 index 7f3b2d67ff0d56072907daeac2129b1fc24ec72e..0000000000000000000000000000000000000000 --- a/pytorch_model-00001-of-00003.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f7785c4057c9b9b0041ea58509467c24be6ef2b54a3c1f241fdea0bc11a43411 -size 9907090895 diff --git a/pytorch_model-00001-of-00028.bin b/pytorch_model-00001-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..afec581487baf96443ee6bec44fac85268c2e577 --- /dev/null +++ b/pytorch_model-00001-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f080290e479e5303e06a8a69bd4ec6835191e40022f90e7f8c5fe3a0ad3059a +size 883756048 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin deleted file mode 100644 index 0360ffe0083a3e889e3bb751813d363c2300772b..0000000000000000000000000000000000000000 --- a/pytorch_model-00002-of-00003.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a659a75e3d8eb1af839aced8892f4c9c9ddd6b8d756361c29eb57436b7f5d9b4 -size 9867486361 diff --git a/pytorch_model-00002-of-00028.bin b/pytorch_model-00002-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..808cfd4793143ccc99342fc3d8e0753bfde42776 --- /dev/null +++ b/pytorch_model-00002-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e3f8fcea4aeeca003b0b228907aa61aa8d8c912ea98f7a99d1d1337348f007 +size 969979357 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin deleted file mode 100644 index 2d4622d92a2a7bd5938743431c4ab3fdc3f1c241..0000000000000000000000000000000000000000 --- a/pytorch_model-00003-of-00003.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3142854fca7fab0d756369c9e055dedc91ec1fa0b4112659448d596fd21e62c0 -size 6666899881 diff --git a/pytorch_model-00003-of-00028.bin b/pytorch_model-00003-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec708e88107bb0590c5974ebc6bcbb1d5e0c1812 --- /dev/null +++ b/pytorch_model-00003-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7856dee5e481e21e6279460c912118afbf3861a58c6593379fb2c7227537dc1 +size 933258973 diff --git a/pytorch_model-00004-of-00028.bin b/pytorch_model-00004-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..30a2e098d1acacd100af9d96420356597ec9285e --- /dev/null +++ b/pytorch_model-00004-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2af83e24ab7ec3642c9716cae975224e01728cc4c47fb711c2e0b223342c62 +size 969979357 diff --git a/pytorch_model-00005-of-00028.bin b/pytorch_model-00005-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e8b35e5636c724a7427f3fc04ae7beb7347baea --- /dev/null +++ b/pytorch_model-00005-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bdb317c89a0e899152d72c2bad92a9c86d858470518d4eedddd3fba3bfcd432 +size 933258973 diff --git a/pytorch_model-00006-of-00028.bin b/pytorch_model-00006-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e8383bac2bc37fd8e1d2806de7e8bc2105a46aa --- /dev/null +++ b/pytorch_model-00006-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26faa44b322949cf4c4178fe081a6ed0e6a3d4f3631e90207f6e353d9089e5a0 +size 969979357 diff --git a/pytorch_model-00007-of-00028.bin b/pytorch_model-00007-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..26f820531df0dd73bc46ba9c363ae772b808c805 --- /dev/null +++ b/pytorch_model-00007-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5db0bfb4162a58425622f134faf10ce652b8ce3d140c39c7bad664e3c4ba33d +size 933258973 diff --git a/pytorch_model-00008-of-00028.bin b/pytorch_model-00008-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5c827504e1f925b85024f7be6eef9f953b7a336 --- /dev/null +++ b/pytorch_model-00008-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca421cc47467d35463bc9f24a79d4943c0a79e76fc22853f7e606019e0d3755 +size 969979357 diff --git a/pytorch_model-00009-of-00028.bin b/pytorch_model-00009-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..7afaf9e7ba3a36c1519e7620297fbf54b084c1aa --- /dev/null +++ b/pytorch_model-00009-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb042e180e8c3e919d9229893d835c218686a5d75b94e2b38a2b4aa1fda7335e +size 933258973 diff --git a/pytorch_model-00010-of-00028.bin b/pytorch_model-00010-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf28fe250c0d18974421ead9a0c4b9d410688082 --- /dev/null +++ b/pytorch_model-00010-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4074fc82c1bf6eb9bcda2b54d674c1c78b883e8dfbd53087894a1e8b3f0c2d +size 969979357 diff --git a/pytorch_model-00011-of-00028.bin b/pytorch_model-00011-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9bb53380b8d315480e0b5b0f215dd26f51d5e86 --- /dev/null +++ b/pytorch_model-00011-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eecbb52e0cc739c8e703da53c4eb7d0c6fda6a42a7857e9ddda208155c87ad01 +size 933258973 diff --git a/pytorch_model-00012-of-00028.bin b/pytorch_model-00012-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..361e4fcd0f576538509915870a32daee03302b69 --- /dev/null +++ b/pytorch_model-00012-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87ef24cd81803688bf360749ee5e18bd89685ff93ca9e68fa0aac5557a9a7b1 +size 969979357 diff --git a/pytorch_model-00013-of-00028.bin b/pytorch_model-00013-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c397b1990332c581bd0243befc30c63d954ca73 --- /dev/null +++ b/pytorch_model-00013-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138102a2c3a30335b2b62b989f08715cb2b972724cd22aa25396849e6d3a8789 +size 933258973 diff --git a/pytorch_model-00014-of-00028.bin b/pytorch_model-00014-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..e497bf4834a2d750e5cc2420a674045f15f8e118 --- /dev/null +++ b/pytorch_model-00014-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b0a556a74c60d9cb20ef26fda6f915bc7a3a0cd4465f7fa43c1b6b5f1bef127 +size 969979357 diff --git a/pytorch_model-00015-of-00028.bin b/pytorch_model-00015-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..5b6089d793271cd1380ba3a1e2dd0f4f50e87721 --- /dev/null +++ b/pytorch_model-00015-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db7c4c907df33969791673f52e60517647388735897549f703fe13c94fc7da7 +size 933258973 diff --git a/pytorch_model-00016-of-00028.bin b/pytorch_model-00016-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..44e6c01738d38f43fb6c175f733feb652c05ff4e --- /dev/null +++ b/pytorch_model-00016-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f977ca91f477e744fb9421cb0b252c87ff7be17d76fe3e52b9fd83ce7e6705 +size 969979357 diff --git a/pytorch_model-00017-of-00028.bin b/pytorch_model-00017-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..db8bd5a3c1707265e77ad8467d13e7a673d411b7 --- /dev/null +++ b/pytorch_model-00017-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b06f96ca0776e21ec4fa3fcb6e791c61bbab70da108e12c3bca27be72bb8800 +size 933258973 diff --git a/pytorch_model-00018-of-00028.bin b/pytorch_model-00018-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..71e0523eed925a4c130425fb06a422f47f7bb12d --- /dev/null +++ b/pytorch_model-00018-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a676d42cdc8268f07e3c838e59790d4657e5030ef93f60612aa991fc6e837ed8 +size 969979357 diff --git a/pytorch_model-00019-of-00028.bin b/pytorch_model-00019-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d4055f38200d3c0f8bc1bacab0bb90dfaf4869f --- /dev/null +++ b/pytorch_model-00019-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac69f5e9e55dc3833aa97bb44a3c672d27f6c08cecd312cd48ccd68f162b189 +size 933258973 diff --git a/pytorch_model-00020-of-00028.bin b/pytorch_model-00020-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..509b3f47b99067c07194e84184a52e0f9e7a1061 --- /dev/null +++ b/pytorch_model-00020-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ae03c9629fc11ec66453e749f64f8562d0d7da85cc913c405cec5d151f4609 +size 969979357 diff --git a/pytorch_model-00021-of-00028.bin b/pytorch_model-00021-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..a56982125acf04a6f969baa98be6e6fe7fd77d32 --- /dev/null +++ b/pytorch_model-00021-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b89969e3b83c1bb381bfc11f047a0d9e566b1140bdd2c28e970a095574dfbc7 +size 933258973 diff --git a/pytorch_model-00022-of-00028.bin b/pytorch_model-00022-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..fb9fc0f77882a39ce8f231bb15ccd263d54728bc --- /dev/null +++ b/pytorch_model-00022-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ca57e1743afbc20875ac0969550f0ecc9399b043b1bca38e4f7d2aaa55cecc +size 969979357 diff --git a/pytorch_model-00023-of-00028.bin b/pytorch_model-00023-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..b47559f87ad1cf38e7664c5e25a16992215c4bd5 --- /dev/null +++ b/pytorch_model-00023-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5f12f4af7eebb6b15bb7d719987cb71c741189e49e12917aa6e4a5fa517c95 +size 933258973 diff --git a/pytorch_model-00024-of-00028.bin b/pytorch_model-00024-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..db219b765018bcc3b7afb4dab9075fec7ca39808 --- /dev/null +++ b/pytorch_model-00024-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a736b9e84a9b61c498c5ff3db3daa8259df7480bf3d7deed5d670776da44d7 +size 969979357 diff --git a/pytorch_model-00025-of-00028.bin b/pytorch_model-00025-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4851a4925a38ad6051890fe45bda6785c25e2c0 --- /dev/null +++ b/pytorch_model-00025-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e020510af416faa55316229d98a014bae0d141fd9123ea7f68dd91a3fde4b6d8 +size 933258973 diff --git a/pytorch_model-00026-of-00028.bin b/pytorch_model-00026-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..8fa92251ef2898ac892d711b9e7362c01d2fc2ed --- /dev/null +++ b/pytorch_model-00026-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ef634f1b95af318689594906236ab02fe1b1c50c86e274b1cb1d3376c7fa4e +size 969979357 diff --git a/pytorch_model-00027-of-00028.bin b/pytorch_model-00027-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..32d0cee1156b5941e14de7c0d0f349fc02790d2c --- /dev/null +++ b/pytorch_model-00027-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1727a61c26d6ed8beca461ae62076efb47b34b6cb2a429ec20302f1301ed32e +size 933258973 diff --git a/pytorch_model-00028-of-00028.bin b/pytorch_model-00028-of-00028.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ef1a08258bcecf9f20f0dbb66228de766d0a59d --- /dev/null +++ b/pytorch_model-00028-of-00028.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af23940413238812345cb771ee7453768da17cdf3d1c8c57bdde19296a19512 +size 815628671 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json index 529dcf68abc8f32ffefdb086fe1ad0a06d0bbae0..51abf58f98f6927965183592ac02b7ca820b03b2 100644 --- a/pytorch_model.bin.index.json +++ b/pytorch_model.bin.index.json @@ -3,408 +3,408 @@ "total_size": 26441338880 }, "weight_map": { - "lm_head.weight": "pytorch_model-00003-of-00003.bin", - "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", - "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", - "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", - "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", - "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", - "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", - "model.norm.weight": "pytorch_model-00003-of-00003.bin" + "lm_head.weight": "pytorch_model-00028-of-00028.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00028.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00028.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00028.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00028.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00028.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00028.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00028.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00028.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00028.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00028.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00028.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00009-of-00028.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00028.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00010-of-00028.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00028.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00028.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00011-of-00028.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00028.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00012-of-00028.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00028.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00028.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00013-of-00028.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00028.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00028.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00028.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00014-of-00028.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00028.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00028.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00015-of-00028.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00028.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00016-of-00028.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00028.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00028.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00017-of-00028.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00028.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00018-of-00028.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00028.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00028.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00019-of-00028.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00028.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00020-of-00028.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00028.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00028.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00028.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00028.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00021-of-00028.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00028.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00022-of-00028.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00028.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00028.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00023-of-00028.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00028.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00024-of-00028.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00028.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00028.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00025-of-00028.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00028.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00026-of-00028.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00028.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00028-of-00028.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00028-of-00028.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00028-of-00028.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00028-of-00028.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00028.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00027-of-00028.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00028.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00028.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00028.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00028.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00005-of-00028.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00028.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00006-of-00028.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00028.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00008-of-00028.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00028.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00007-of-00028.bin", + "model.norm.weight": "pytorch_model-00028-of-00028.bin" } }