diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..e41416ddd79948246ea2dced6800ea3cd531c424 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..1d76fef819a0764e07f9588816d6d418b1f98f6c --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "mythologic-70b", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.34.0.dev0", + "use_cache": false, + "vocab_size": 32001 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f5a78aa5c2e5fa46d5cf48725e7ae60dc6d4d666 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.34.0.dev0", + "use_cache": false +} diff --git a/pytorch_model-00001-of-00081.bin b/pytorch_model-00001-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..f50266311bf2d7b878be8a29802e12bbc5e00728 --- /dev/null +++ b/pytorch_model-00001-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5422baf9db773a8f2f53cc8182e0e50df592e55f67b3590192c0461603f2fcb4 +size 1765821200 diff --git a/pytorch_model-00002-of-00081.bin b/pytorch_model-00002-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..43cfb35b83379c37da92b1332538291d4c7dbc28 --- /dev/null +++ b/pytorch_model-00002-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:106ff658999b7d90387fbcf544d324df7ad9e0bd5afa05d7093be4b795eca4ea +size 1711312242 diff --git a/pytorch_model-00003-of-00081.bin b/pytorch_model-00003-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..9900b10fbfe7972fcbd72262094170dff56d2601 --- /dev/null +++ b/pytorch_model-00003-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03881333f9762df851652319b097dabf3001b4d193763242b2efb0082df781d7 +size 1711312242 diff --git a/pytorch_model-00004-of-00081.bin b/pytorch_model-00004-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc931dd70c08c684d0c118328c5aa229920537bc --- /dev/null +++ b/pytorch_model-00004-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9823220207948c0d485e3accf5f8891a7a52db9c11bf0c4176494fcc0c180d15 +size 1711312242 diff --git a/pytorch_model-00005-of-00081.bin b/pytorch_model-00005-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..55a9470810359e1bbb42ab8174cb4b7680028b15 --- /dev/null +++ b/pytorch_model-00005-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504f0d98992f676176bb26815afc6d6e0bc5a7e5f1ff38726d2fcd1d580c03b2 +size 1711312242 diff --git a/pytorch_model-00006-of-00081.bin b/pytorch_model-00006-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..62d5c05c744a2978ab3361144c762c71b68cb920 --- /dev/null +++ b/pytorch_model-00006-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343c17a49337c7227c267b1f2fb8785962db6456c8e85f83b75801e1c702fc25 +size 1711312242 diff --git a/pytorch_model-00007-of-00081.bin b/pytorch_model-00007-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..34672548bedc426b5ccc6796fe9b54b7f7e3ccb0 --- /dev/null +++ b/pytorch_model-00007-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5fb556e4b8a82a0511433f2984929642447145c9b1d350611144ccf4c7f531 +size 1711312242 diff --git a/pytorch_model-00008-of-00081.bin b/pytorch_model-00008-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5fce3f7f6c8d955706e197d65a7e1298f0af1dc --- /dev/null +++ b/pytorch_model-00008-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ef8816d2a34dbb3da90114a5566602aa097769430ce1ecaac08b5474fc1d5a +size 1711312242 diff --git a/pytorch_model-00009-of-00081.bin b/pytorch_model-00009-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d6e864b8e4317fe6339cbc1b91b2d4b2ae77c41 --- /dev/null +++ b/pytorch_model-00009-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adb4fd7ff450cc547466f41ea60e028a49c3dc7fd3720eb3fae9b392b04a712 +size 1711312242 diff --git a/pytorch_model-00010-of-00081.bin b/pytorch_model-00010-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb9ec547310b3ab743ecf38e3d0f6e8b2cf84165 --- /dev/null +++ b/pytorch_model-00010-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb0d76f742d56e986ffdb0b63321e75f6447d253f18b50b127c5776cb205235 +size 1711312242 diff --git a/pytorch_model-00011-of-00081.bin b/pytorch_model-00011-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..60f8cc12b7f81729a5518b40777c4bb1278426e1 --- /dev/null +++ b/pytorch_model-00011-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b550ab18844a015a0b521766abb46cef95d45a2a5adef03a95088d5bfcbb9ef +size 1711312242 diff --git a/pytorch_model-00012-of-00081.bin b/pytorch_model-00012-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e79d50da32c6678d77b909a8c11fb05f74c6bd3c --- /dev/null +++ b/pytorch_model-00012-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530f0a478fbe0696026602ff08484cf8dfc12fbbf98a68b5351096c3b8144d02 +size 1711312242 diff --git a/pytorch_model-00013-of-00081.bin b/pytorch_model-00013-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..8a99c7381a74e167c78ed103a5db346be1f607a0 --- /dev/null +++ b/pytorch_model-00013-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91044dd6b7b5c71e64ed3157ec1b4c0148457f42a4208727ad6573f24316f2ae +size 1711312242 diff --git a/pytorch_model-00014-of-00081.bin b/pytorch_model-00014-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..26665c1f29b3f31e7454cbfa0c2f16d53e86dd03 --- /dev/null +++ b/pytorch_model-00014-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c5377bd634e2313ae6e31b60f7fe1d5877d4753ea86a1d456378fa65ab632c7 +size 1711312242 diff --git a/pytorch_model-00015-of-00081.bin b/pytorch_model-00015-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..05a5db911e61d15f32aaaa6286401e57e6050669 --- /dev/null +++ b/pytorch_model-00015-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e814b373a025384cba0c18f9624f4aa76b8e6afb1bb48f61a79fdfbd9d735f71 +size 1711312242 diff --git a/pytorch_model-00016-of-00081.bin b/pytorch_model-00016-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc8bb3e5273e8d5877bf3c95cb47b90cc9910fbc --- /dev/null +++ b/pytorch_model-00016-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6d3eba3e6a8400446c3d0a2f236bfbe4225d92e38af1daa9a6d35eea1ca08e +size 1711312242 diff --git a/pytorch_model-00017-of-00081.bin b/pytorch_model-00017-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..7e54169c21edcb5e3b2ac8481aa43e6e65ab0975 --- /dev/null +++ b/pytorch_model-00017-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5375158f94ef7f917e63dc3c8132249b7f949c5ccd9b154c8353f7ecc9cfb752 +size 1711312242 diff --git a/pytorch_model-00018-of-00081.bin b/pytorch_model-00018-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e489522a33efd6d446b3b1ef957e4bf9365335e8 --- /dev/null +++ b/pytorch_model-00018-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607088a42225e3d9daf79f6a231fb6bfc73146be484bbb2f0baf5602d51d3350 +size 1711312242 diff --git a/pytorch_model-00019-of-00081.bin b/pytorch_model-00019-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..17c22ea026f527875282054dc11a0e5a3a8a53f3 --- /dev/null +++ b/pytorch_model-00019-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff21545d1a7d9b7c5a5b911da651224780ead6a8a033111390c3ceb96ca33008 +size 1711312242 diff --git a/pytorch_model-00020-of-00081.bin b/pytorch_model-00020-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e6ea1659e0ab7c4ea59a93f3beed2b9e3754e00 --- /dev/null +++ b/pytorch_model-00020-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5d30038d5f6d0ae05ab80160c294be42ca68b7110e0dbb45bef1926781d603 +size 1711312242 diff --git a/pytorch_model-00021-of-00081.bin b/pytorch_model-00021-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..1cb050ce83fb11384106d35892cd0c23bf2a83e0 --- /dev/null +++ b/pytorch_model-00021-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e156454c1cc4f1c84fe3c87ec5af558966691bf02f608560376cc3b3c1c25b +size 1711312242 diff --git a/pytorch_model-00022-of-00081.bin b/pytorch_model-00022-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..17a1a026fa4e3fbc2046dbda24e5e87a5711b339 --- /dev/null +++ b/pytorch_model-00022-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f56e45ce6ebc44a52dc8d1ac1f2b042727922a58a0aefdd5083a772e4924e31 +size 1711312242 diff --git a/pytorch_model-00023-of-00081.bin b/pytorch_model-00023-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d2bb672ca825f2fa18f1d70335121c617b901b5 --- /dev/null +++ b/pytorch_model-00023-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200c6164f1f9e697d856808bddf71f5a42722ba2c2d62ae38f318a7b9e1d07e4 +size 1711312242 diff --git a/pytorch_model-00024-of-00081.bin b/pytorch_model-00024-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb708eb36d999edeb4943bdd632769ae7f1efb39 --- /dev/null +++ b/pytorch_model-00024-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777655046184356aa8b827255d577eeac82332ba6a74ec1bc372d8c612d1f18d +size 1711312242 diff --git a/pytorch_model-00025-of-00081.bin b/pytorch_model-00025-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..165b693b3cb826b2e567c89645e0727172b817bd --- /dev/null +++ b/pytorch_model-00025-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aae49da7cf5300830f42ba83249a4b5b55c7a0af6bcb05bdce51b9076fb6bdf +size 1711312242 diff --git a/pytorch_model-00026-of-00081.bin b/pytorch_model-00026-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..341a6a4cbafd93f47e082cc56acd7d4ffdce73fb --- /dev/null +++ b/pytorch_model-00026-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e458342ed01b99df63f7ccf6e46242ff8f620c79bca86b92f2639c4e2c6cf85f +size 1711312242 diff --git a/pytorch_model-00027-of-00081.bin b/pytorch_model-00027-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..eca8e3e2021ae1cc3a0050e65d09e42969aea2f9 --- /dev/null +++ b/pytorch_model-00027-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0af2a221ef24236c0170cdbae447d12c622a5a5afbea8adbd5b9774251a208 +size 1711312242 diff --git a/pytorch_model-00028-of-00081.bin b/pytorch_model-00028-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..676c3819f525995963cf9ad420152f16cf749092 --- /dev/null +++ b/pytorch_model-00028-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01eae9f7a533ac8fa184bf1ab9459f0410ceef43e14ce202788af524c1ff0e87 +size 1711312242 diff --git a/pytorch_model-00029-of-00081.bin b/pytorch_model-00029-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7278f8ebd319600f640c576ae91e58c8f9cbcbb --- /dev/null +++ b/pytorch_model-00029-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3429c99b6496843e892c7977df9196254efebf93b1fd00b9be230946b853978 +size 1711312242 diff --git a/pytorch_model-00030-of-00081.bin b/pytorch_model-00030-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..db6c0820ffb52b527938761fe017a198e411109f --- /dev/null +++ b/pytorch_model-00030-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9be376563b6210388084c1413dffcd81b234ebe0161abd9089d9ed93959af64 +size 1711312242 diff --git a/pytorch_model-00031-of-00081.bin b/pytorch_model-00031-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..8356c22f269f07dc854d4a82fa6f27522986c14c --- /dev/null +++ b/pytorch_model-00031-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaea7dd4b50690f0523c43a205f7e85cac692793b5815263107a0aed8993d188 +size 1711312242 diff --git a/pytorch_model-00032-of-00081.bin b/pytorch_model-00032-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5a070ac80bc6fc19a617c21a058d71c1ab4c3c5 --- /dev/null +++ b/pytorch_model-00032-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f86967c0ff706e331f9e612c8bc96d8a70840143d72395d31310f5ccf8368c +size 1711312242 diff --git a/pytorch_model-00033-of-00081.bin b/pytorch_model-00033-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5c8c1b63a60aa985acc0955767f6f11c8890f8b --- /dev/null +++ b/pytorch_model-00033-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c15e26cc51ceac43919046fe8c8f8b2e328708d47d3d7d502ffc694432711669 +size 1711312242 diff --git a/pytorch_model-00034-of-00081.bin b/pytorch_model-00034-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfb805357e18ad23c53138b97ae070d2bef83653 --- /dev/null +++ b/pytorch_model-00034-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e855a3c4d55240db174be6c39f3bcbc3956d9aed4de48f62ffa4d680776dd462 +size 1711312242 diff --git a/pytorch_model-00035-of-00081.bin b/pytorch_model-00035-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..ede0e36c0b9620c42be6fbdf36582bfb23a46bc7 --- /dev/null +++ b/pytorch_model-00035-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d57fb7b519f933f87ab9e6738178dbf42755e565db445afb8a7907b9edafb63 +size 1711312242 diff --git a/pytorch_model-00036-of-00081.bin b/pytorch_model-00036-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..11452dbd73dc950331b7e40cb8c82f723a5f0acb --- /dev/null +++ b/pytorch_model-00036-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1fecd437c0d9072705751934c7e7b42856bbf2fd869f93f3df182cc97bbd9a +size 1711312242 diff --git a/pytorch_model-00037-of-00081.bin b/pytorch_model-00037-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..1068ef07c63f3abfdb33411d95958212ea9e2597 --- /dev/null +++ b/pytorch_model-00037-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3e5377c8c88639291b9813f3edb5cf0617bc0de9ae81034871e49c62215178 +size 1711312242 diff --git a/pytorch_model-00038-of-00081.bin b/pytorch_model-00038-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e4ce590311f0ff2bacdfcc9a5fc57814b7d7abb --- /dev/null +++ b/pytorch_model-00038-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6a65ca79727ff9f4aa8fbd2ebc0e02529007ba56438f7a03b80974dfc83d44 +size 1711312242 diff --git a/pytorch_model-00039-of-00081.bin b/pytorch_model-00039-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd08d8e0e74693718b5c3ed955a75d24304d79c6 --- /dev/null +++ b/pytorch_model-00039-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bad96adb4847db60d60479a372ec9754a24345626315b5b69d9afaac39b0e41 +size 1711312242 diff --git a/pytorch_model-00040-of-00081.bin b/pytorch_model-00040-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ca3c12aca0c5c2564de4092b5b8f446a54446f2 --- /dev/null +++ b/pytorch_model-00040-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce852672d5d42a4bcb5c286d6481409895218f6423491764d4cc024b71de0131 +size 1711312242 diff --git a/pytorch_model-00041-of-00081.bin b/pytorch_model-00041-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e2e6b67940fbd135e8152eed9f3976278aa71382 --- /dev/null +++ b/pytorch_model-00041-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02a948542aa298f345942940f3076c6fc6c130395580503c717e4983ac9dc3b +size 1711312242 diff --git a/pytorch_model-00042-of-00081.bin b/pytorch_model-00042-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..c5ad85e52bc1d977a1ac0768857c90a6bdc00528 --- /dev/null +++ b/pytorch_model-00042-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64523cd39ab8c42001625b9dae48326522eb9e9c89af3e9a74dcced6e871479c +size 1711312242 diff --git a/pytorch_model-00043-of-00081.bin b/pytorch_model-00043-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..07d6f4b9520c394d859e6dc91c6c9eefb087068b --- /dev/null +++ b/pytorch_model-00043-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b360d9e04860354cf1b5916386be7f5419aa40e487fbbc9092d7c1e0a1c605 +size 1711312242 diff --git a/pytorch_model-00044-of-00081.bin b/pytorch_model-00044-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..59845c205ec2e324ff98312631e4c73512f80a87 --- /dev/null +++ b/pytorch_model-00044-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542dfeb26bec58ead97429b3e1e5e05b5c270301b1153036bbb59b7de2a125cd +size 1711312242 diff --git a/pytorch_model-00045-of-00081.bin b/pytorch_model-00045-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..42df0c4c83a3434568eefefcf22e3106edca81b7 --- /dev/null +++ b/pytorch_model-00045-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de810bfdba500527e66d6609e9cf101741245232b56b458ce0942720bb6a34c +size 1711312242 diff --git a/pytorch_model-00046-of-00081.bin b/pytorch_model-00046-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e10f4bfa3eaad6c61e16b8ad229cc33fb79deeb --- /dev/null +++ b/pytorch_model-00046-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:676ddf551d5c999c16e95c4b6fb59b18a3e09c8c6aea43b9008543526a19be33 +size 1711312242 diff --git a/pytorch_model-00047-of-00081.bin b/pytorch_model-00047-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..348328a03bab92726357b5f230a83bbc159cd19c --- /dev/null +++ b/pytorch_model-00047-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24cf22e28f16614924b3ea339a2a19f5f8dbc7244aa05b2896a2d5da99143eb +size 1711312242 diff --git a/pytorch_model-00048-of-00081.bin b/pytorch_model-00048-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6f9b95c497a5040fa85eff64da7751da90291fa --- /dev/null +++ b/pytorch_model-00048-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5e0695040a201ef0bf2a120ac8d922a4846beaab8c6108d5be11e4f133818f +size 1711312242 diff --git a/pytorch_model-00049-of-00081.bin b/pytorch_model-00049-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..44d9a3fb80985b14c020414c44e66bc78535d522 --- /dev/null +++ b/pytorch_model-00049-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9276dfe35d1305fff035cf6ada95e270678c8655855da66d89d9bbf4fa535681 +size 1711312242 diff --git a/pytorch_model-00050-of-00081.bin b/pytorch_model-00050-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..a4d3b18f19718e15b95511af2c72a769a666be27 --- /dev/null +++ b/pytorch_model-00050-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47c6cdce2ef79e4b6fe53d3ed37224bc1cba1be0803ea199bf8e02028e465e9 +size 1711312242 diff --git a/pytorch_model-00051-of-00081.bin b/pytorch_model-00051-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..b078b42a337d52fd28e1c65757e5dc227412c288 --- /dev/null +++ b/pytorch_model-00051-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a09778875e46356317bdfa026fad506ca95c3e28f5a99a86da7e3266e5a8001d +size 1711312242 diff --git a/pytorch_model-00052-of-00081.bin b/pytorch_model-00052-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e126dc68b7fb55090698a7300428227e9c99fe0 --- /dev/null +++ b/pytorch_model-00052-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82bdaa406285824e1af630565efc9fc40d614a54e6ba94b3248560c861a47273 +size 1711312242 diff --git a/pytorch_model-00053-of-00081.bin b/pytorch_model-00053-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6dd8cf1b0d2aba6deb1404f288b2fb4bf3eb076 --- /dev/null +++ b/pytorch_model-00053-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825b406efbde79025604bd8e25f21dfd319ed278559eabcf1a657508d9fdd117 +size 1711312242 diff --git a/pytorch_model-00054-of-00081.bin b/pytorch_model-00054-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..93e77e473e1f93656f9c6208ea7b818e287b0657 --- /dev/null +++ b/pytorch_model-00054-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ebc0da88b1630debc3d7cb078f0f179746f8c079dca4f3aa8a40a69e1d0164 +size 1711312242 diff --git a/pytorch_model-00055-of-00081.bin b/pytorch_model-00055-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..7df3811919c2c6dedd5138d58308f766ee1742f6 --- /dev/null +++ b/pytorch_model-00055-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a24fe0a690eb7afb54a96057ebdee80e6eb9e2600416561271c071a31218ff3 +size 1711312242 diff --git a/pytorch_model-00056-of-00081.bin b/pytorch_model-00056-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc0d12665ca072b7e5f81f0c4ad35cb2f8cab077 --- /dev/null +++ b/pytorch_model-00056-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c37c80ead1b80d7f940f46a777047d57c05eb0e73797a18308f9ba71c026e2 +size 1711312242 diff --git a/pytorch_model-00057-of-00081.bin b/pytorch_model-00057-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ee9ef6331b8d439fb9a0450bb74fae6de2bd426 --- /dev/null +++ b/pytorch_model-00057-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde035715c07b7740382329c530101c7f98f150e68826789182689b8b3ed1dd2 +size 1711312242 diff --git a/pytorch_model-00058-of-00081.bin b/pytorch_model-00058-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a29e0d3e15be6a277959478daf2f86e9d85c7f2 --- /dev/null +++ b/pytorch_model-00058-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1503f8b05c69f7e2fa10d0e5388c1503a20d3228b7c66c98fcde50e630d6f7 +size 1711312242 diff --git a/pytorch_model-00059-of-00081.bin b/pytorch_model-00059-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b26164e05923ecbe2e5d5c17d0032ad3aeb4074 --- /dev/null +++ b/pytorch_model-00059-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272f48bcf4066c8dc3766cd7539e0f41ff19296d422ed663fabd1b02c0099ab1 +size 1711312242 diff --git a/pytorch_model-00060-of-00081.bin b/pytorch_model-00060-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..f6b35761aeb2be266f9d566c9fb5fbb8557245e9 --- /dev/null +++ b/pytorch_model-00060-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f66c68725fa19898f5e14aba8e4a4e10724b9203bd7a8f2118f5370bcfed44e3 +size 1711312242 diff --git a/pytorch_model-00061-of-00081.bin b/pytorch_model-00061-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb77d7d9d27105d27cd2c622aafa65398fed6d9d --- /dev/null +++ b/pytorch_model-00061-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b0d49b73491bf60eee2e8f0024c0d0d6022cd820da5f7b8e214dad576ea07a +size 1711312242 diff --git a/pytorch_model-00062-of-00081.bin b/pytorch_model-00062-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..c13d57a136401767b61d6b7f14de05e0b2f1868e --- /dev/null +++ b/pytorch_model-00062-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d380c94b20b9410fb8456a8f93cebaa576e1ff653c50f322c5f53221b675df7 +size 1711312242 diff --git a/pytorch_model-00063-of-00081.bin b/pytorch_model-00063-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..110da51ea495e1c6c18de8e71c9b80b74a9999bb --- /dev/null +++ b/pytorch_model-00063-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76551777889f78afe35584ba18a4cb6b3a2b76e92869c8022cca5c1a9192f80c +size 1711312242 diff --git a/pytorch_model-00064-of-00081.bin b/pytorch_model-00064-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..53b240759984e04c4cd342959da50c4b2d65aa74 --- /dev/null +++ b/pytorch_model-00064-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677fff2cfd6f503c4d7abf879bac3c66ee5bd4485ad01263e50d1c808298d4f6 +size 1711312242 diff --git a/pytorch_model-00065-of-00081.bin b/pytorch_model-00065-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e8a5405ffea8845e952327f2728b27aa988bec43 --- /dev/null +++ b/pytorch_model-00065-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de0d4c4d58f3b16e0e1a1b9409302c2b0beb5558382d3afc6dc524751eb4763 +size 1711312242 diff --git a/pytorch_model-00066-of-00081.bin b/pytorch_model-00066-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b77a471e946a0e7a1040e6ada011e1588532910 --- /dev/null +++ b/pytorch_model-00066-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c654dfd2170c94ccf38d72aa2f85e7d821110758eb7a89c1787fbc4747842b7e +size 1711312242 diff --git a/pytorch_model-00067-of-00081.bin b/pytorch_model-00067-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d3c886ff160b2790e71a313738b17a26c0b5852 --- /dev/null +++ b/pytorch_model-00067-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8bccf29386ac730d504106cdb3feef6826751a534e80331dd4d5fa027e688f0 +size 1711312242 diff --git a/pytorch_model-00068-of-00081.bin b/pytorch_model-00068-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef0cdf9e59076151c9f3a20e3df08e37c5c8c10e --- /dev/null +++ b/pytorch_model-00068-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0464d15ede44c6c6c0c320fc42e1486103fd9dbfe7498134942b83a6a26244be +size 1711312242 diff --git a/pytorch_model-00069-of-00081.bin b/pytorch_model-00069-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c1851e80c0afa641ae04029916895d1a6fa0fdf --- /dev/null +++ b/pytorch_model-00069-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f469535e60eb9793d8f2e5b0ed5653e43f4071626786575ab56373b5bf94e1c +size 1711312242 diff --git a/pytorch_model-00070-of-00081.bin b/pytorch_model-00070-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee38d44d2534f4f0eb5196ded9d1b615b3787a0e --- /dev/null +++ b/pytorch_model-00070-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd6d5840e83a6e5ec96fc63f8d8ec42b8898773f4fe56c423862a123290268b7 +size 1711312242 diff --git a/pytorch_model-00071-of-00081.bin b/pytorch_model-00071-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f1148e83c07eef6dae7423960e3fc814189bfab --- /dev/null +++ b/pytorch_model-00071-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970dd50f25253b9956df8aab37214fac40f0ebb1256b0362f2be073c12ffc7c9 +size 1711312242 diff --git a/pytorch_model-00072-of-00081.bin b/pytorch_model-00072-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..1197dc10f7faed102d44d09b5de79ceef0d05c6d --- /dev/null +++ b/pytorch_model-00072-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c95d1606663f950fea37dfd4dfc38391f6760e66265ac949061cf2177fe9e6 +size 1711312242 diff --git a/pytorch_model-00073-of-00081.bin b/pytorch_model-00073-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..4980dbf481dfbfc0206b68c83b262cfbf649eb36 --- /dev/null +++ b/pytorch_model-00073-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31f6c4ed53d47b66fef9249d4f261e0d1ec6f7b543881645ab8d4c59acb0182 +size 1711312242 diff --git a/pytorch_model-00074-of-00081.bin b/pytorch_model-00074-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..c60eeac3f1fdb61d2d890b50e820fd927dafe2de --- /dev/null +++ b/pytorch_model-00074-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b936500889c6a20024d53dd51042317474b781f7bafdddaf7f791df88192ba +size 1711312242 diff --git a/pytorch_model-00075-of-00081.bin b/pytorch_model-00075-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..38afd07c02f9592380d52bd6bd03fa37b77c887a --- /dev/null +++ b/pytorch_model-00075-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cacd49d661346c681307a0aa1555cb2fb3b8ed6e542a9f09564c79511839645 +size 1711312242 diff --git a/pytorch_model-00076-of-00081.bin b/pytorch_model-00076-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..99cca383d15b76dd492cff36a0aa3b802dbf7275 --- /dev/null +++ b/pytorch_model-00076-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e265fb4cfb537a6cd866e5dcd68965b1de4272c3b6826c871c6fcf2d66db84 +size 1711312242 diff --git a/pytorch_model-00077-of-00081.bin b/pytorch_model-00077-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..2fb5cc099cd8637848b0777b8f780b5bfe56c9c7 --- /dev/null +++ b/pytorch_model-00077-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e6ba0a08011472fd73204ec6d4d73e9e2a7b57a0bbd38647ff7e5edc6cdd9d +size 1711312242 diff --git a/pytorch_model-00078-of-00081.bin b/pytorch_model-00078-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..4edf567c98f73477638f7e0c4fe1cd43133483f6 --- /dev/null +++ b/pytorch_model-00078-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583bb65a0bc28fa8ed7b8a00c04f4264fdcb405daaa6e4423b56a38a9ee02bbe +size 1711312242 diff --git a/pytorch_model-00079-of-00081.bin b/pytorch_model-00079-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..daa93595c07a736f73a0cf8d986947c2f5f1dee4 --- /dev/null +++ b/pytorch_model-00079-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c43580c73e0e7f9483be549e31f093ae1d2f6455389c942153976fcdf61123 +size 1711312242 diff --git a/pytorch_model-00080-of-00081.bin b/pytorch_model-00080-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f94ee14d84beba3a756b37dfea31d60590e5ffb --- /dev/null +++ b/pytorch_model-00080-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870908c8bc53353fe72aca20fcb6dd331e0c3a7c9aaf40a6c22e81f7370e3e33 +size 1711312242 diff --git a/pytorch_model-00081-of-00081.bin b/pytorch_model-00081-of-00081.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7fd850f6b8f6b0cb80107a8173ca8ce0a9400ea --- /dev/null +++ b/pytorch_model-00081-of-00081.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef82e5b2f38aa60cbd765a78eb1845df016cdc383ac397c13b0b3571c295338b +size 994117742 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000000000000000000000000000000000000..1fc6ee72f8f8ccf957e2d681bc9dc7cd27b0d0b0 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 137953329152 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00081-of-00081.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00081.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00081.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00012-of-00081.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00013-of-00081.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00014-of-00081.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00015-of-00081.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00016-of-00081.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00017-of-00081.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00018-of-00081.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00019-of-00081.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00020-of-00081.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00081.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00021-of-00081.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00022-of-00081.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00023-of-00081.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00024-of-00081.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00025-of-00081.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00026-of-00081.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00027-of-00081.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00028-of-00081.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00029-of-00081.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00030-of-00081.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00081.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00031-of-00081.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00032-of-00081.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00033-of-00081.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00034-of-00081.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00035-of-00081.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00036-of-00081.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00037-of-00081.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00038-of-00081.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00039-of-00081.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00040-of-00081.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00005-of-00081.bin", + "model.layers.40.input_layernorm.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.40.mlp.down_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.40.mlp.up_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00041-of-00081.bin", + "model.layers.41.input_layernorm.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.41.mlp.down_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.41.mlp.up_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00042-of-00081.bin", + "model.layers.42.input_layernorm.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.42.mlp.down_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.42.mlp.up_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00043-of-00081.bin", + "model.layers.43.input_layernorm.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.43.mlp.down_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.43.mlp.up_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00044-of-00081.bin", + "model.layers.44.input_layernorm.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.44.mlp.down_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.44.mlp.up_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00045-of-00081.bin", + "model.layers.45.input_layernorm.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.45.mlp.down_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.45.mlp.up_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00046-of-00081.bin", + "model.layers.46.input_layernorm.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.46.mlp.down_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.46.mlp.up_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00047-of-00081.bin", + "model.layers.47.input_layernorm.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.47.mlp.down_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.47.mlp.up_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00048-of-00081.bin", + "model.layers.48.input_layernorm.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.48.mlp.down_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.48.mlp.up_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00049-of-00081.bin", + "model.layers.49.input_layernorm.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.49.mlp.down_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.49.mlp.up_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00050-of-00081.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00006-of-00081.bin", + "model.layers.50.input_layernorm.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.50.mlp.down_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.50.mlp.up_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00051-of-00081.bin", + "model.layers.51.input_layernorm.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.51.mlp.down_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.51.mlp.up_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00052-of-00081.bin", + "model.layers.52.input_layernorm.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.52.mlp.down_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.52.mlp.up_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00053-of-00081.bin", + "model.layers.53.input_layernorm.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.53.mlp.down_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.53.mlp.up_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00054-of-00081.bin", + "model.layers.54.input_layernorm.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.54.mlp.down_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.54.mlp.up_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00055-of-00081.bin", + "model.layers.55.input_layernorm.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.55.mlp.down_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.55.mlp.up_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00056-of-00081.bin", + "model.layers.56.input_layernorm.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.56.mlp.down_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.56.mlp.up_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00057-of-00081.bin", + "model.layers.57.input_layernorm.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.57.mlp.down_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.57.mlp.up_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00058-of-00081.bin", + "model.layers.58.input_layernorm.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.58.mlp.down_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.58.mlp.up_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00059-of-00081.bin", + "model.layers.59.input_layernorm.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.59.mlp.down_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.59.mlp.up_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00060-of-00081.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00007-of-00081.bin", + "model.layers.60.input_layernorm.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.60.mlp.down_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.60.mlp.up_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00061-of-00081.bin", + "model.layers.61.input_layernorm.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.61.mlp.down_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.61.mlp.up_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00062-of-00081.bin", + "model.layers.62.input_layernorm.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.62.mlp.down_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.62.mlp.up_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00063-of-00081.bin", + "model.layers.63.input_layernorm.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.63.mlp.down_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.63.mlp.up_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00064-of-00081.bin", + "model.layers.64.input_layernorm.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.64.mlp.down_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.64.mlp.up_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00065-of-00081.bin", + "model.layers.65.input_layernorm.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.65.mlp.down_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.65.mlp.up_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00066-of-00081.bin", + "model.layers.66.input_layernorm.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.66.mlp.down_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.66.mlp.up_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00067-of-00081.bin", + "model.layers.67.input_layernorm.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.67.mlp.down_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.67.mlp.up_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00068-of-00081.bin", + "model.layers.68.input_layernorm.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.68.mlp.down_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.68.mlp.up_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00069-of-00081.bin", + "model.layers.69.input_layernorm.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.69.mlp.down_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.69.mlp.up_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00070-of-00081.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00008-of-00081.bin", + "model.layers.70.input_layernorm.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.70.mlp.down_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.70.mlp.up_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00071-of-00081.bin", + "model.layers.71.input_layernorm.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.71.mlp.down_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.71.mlp.up_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00072-of-00081.bin", + "model.layers.72.input_layernorm.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.72.mlp.down_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.72.mlp.up_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00073-of-00081.bin", + "model.layers.73.input_layernorm.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.73.mlp.down_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.73.mlp.up_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00074-of-00081.bin", + "model.layers.74.input_layernorm.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.74.mlp.down_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.74.mlp.up_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00075-of-00081.bin", + "model.layers.75.input_layernorm.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.75.mlp.down_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.75.mlp.up_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00076-of-00081.bin", + "model.layers.76.input_layernorm.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.76.mlp.down_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.76.mlp.up_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00077-of-00081.bin", + "model.layers.77.input_layernorm.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.77.mlp.down_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.77.mlp.up_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00078-of-00081.bin", + "model.layers.78.input_layernorm.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.78.mlp.down_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.78.mlp.up_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00079-of-00081.bin", + "model.layers.79.input_layernorm.weight": "pytorch_model-00081-of-00081.bin", + "model.layers.79.mlp.down_proj.weight": "pytorch_model-00081-of-00081.bin", + "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.79.mlp.up_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00081-of-00081.bin", + "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00080-of-00081.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00009-of-00081.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00011-of-00081.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00010-of-00081.bin", + "model.norm.weight": "pytorch_model-00081-of-00081.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3f58a5e115855c6ea3cec98accae196ad927222e --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "[PAD]", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..65532c2074f7f407d2d801a559f3d90aa5137f26 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,38 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_default_system_prompt": true, + "use_fast": true +}