diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..7fc80fa680a552ad518b685d550d719cd9788a33 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "/home/llm2/models/llama2/llama-2-13b-hf/", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.29.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1b8b0e206e34293753471f02a46f76e903b8e37 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.9, + "top_p": 0.6, + "transformers_version": "4.29.0" +} diff --git a/pytorch_model-00001-of-00082.bin b/pytorch_model-00001-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a7c46f7a02dd6adb6e2babd0284b11532dfc8d15 --- /dev/null +++ b/pytorch_model-00001-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa8bc3bc263e4a64558ffbc75b815267ceb36cbc73d3a0cd982752ac0b72d74 +size 380110075 diff --git a/pytorch_model-00002-of-00082.bin b/pytorch_model-00002-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..6c2712f387565f9dee2a38d170d2cd5aee970b2a --- /dev/null +++ b/pytorch_model-00002-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17dd1e5e9fa03fdaa0b357ca9fe6bcb512637051ae114963bbb9c295f62f239d +size 298846638 diff --git a/pytorch_model-00003-of-00082.bin b/pytorch_model-00003-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..58a1e187ce53f5b4b7196bd110ae86dc80c865f3 --- /dev/null +++ b/pytorch_model-00003-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3540a4708471964c61bf04f9cdc5d235fe4f7e19a141935be3841d61f206cb16 +size 387996095 diff --git a/pytorch_model-00004-of-00082.bin b/pytorch_model-00004-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..5eda75d9eb42a35192e6152be7082263e72d8535 --- /dev/null +++ b/pytorch_model-00004-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4f55359632d5a61a642504a1f5e076ac1b9ecf5953f8159c9d08372a86c51f +size 387975598 diff --git a/pytorch_model-00005-of-00082.bin b/pytorch_model-00005-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb4067596892f5908dcf2e39723d6b592a71c354 --- /dev/null +++ b/pytorch_model-00005-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7840e3d8d6580b90f6b5820ce56dde428f4353f0577efc5e8f9a8bf8920b1318 +size 351296801 diff --git a/pytorch_model-00006-of-00082.bin b/pytorch_model-00006-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..2144a97dadf8d785dde7f1ad7899e193662d0707 --- /dev/null +++ b/pytorch_model-00006-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11405fe331de8a0d08ba5096a510f712ca0dddd0a2dabfdc61f3e7af9f34b51b +size 283116795 diff --git a/pytorch_model-00007-of-00082.bin b/pytorch_model-00007-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3da80a7ff29d33e7d78eb149dad0adf4c26c5ef9 --- /dev/null +++ b/pytorch_model-00007-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f885d875243eb605b77842dbd85912c77e5cde46cef7f9750f1cf2a68d6a7cde +size 351296801 diff --git a/pytorch_model-00008-of-00082.bin b/pytorch_model-00008-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d630e6d9d93bcb0f815434814187bfd497581247 --- /dev/null +++ b/pytorch_model-00008-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:081b945cea50e9d5c9911a4e4bc082c0a18d94b4389776d3eac8139eba4ca130 +size 283116795 diff --git a/pytorch_model-00009-of-00082.bin b/pytorch_model-00009-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..592977715da6e2b798e9f92bd01d8bf1e44c69b2 --- /dev/null +++ b/pytorch_model-00009-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94df2df060cd30783512b9891604c799c1db932e4edb17c0d210dc861516772d +size 351296801 diff --git a/pytorch_model-00010-of-00082.bin b/pytorch_model-00010-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d762887ae5298b98bd5410afc67683263c11319d --- /dev/null +++ b/pytorch_model-00010-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc65df3d71db65b8770c2dc255243d9c52f84ff5cecf756f56617a9ffe825b9 +size 283116795 diff --git a/pytorch_model-00011-of-00082.bin b/pytorch_model-00011-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a35dc6fa1ceafefbbaf11f76cb5959af51a9dd54 --- /dev/null +++ b/pytorch_model-00011-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbee637d9ad2e6c510ee08f37f0c86d2cd01b3d23f680344a0fc584883bcc654 +size 351296801 diff --git a/pytorch_model-00012-of-00082.bin b/pytorch_model-00012-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..eab61ef53af663365aeb4561baaaa12db6499c5c --- /dev/null +++ b/pytorch_model-00012-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af17aac63c5e2c5a860722b9087fbfbd2177e8ed3b10c7c61fd21b61a3b222cf +size 283116795 diff --git a/pytorch_model-00013-of-00082.bin b/pytorch_model-00013-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b86627af4bded288de20528804de5088a461854f --- /dev/null +++ b/pytorch_model-00013-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa4469c8c10465859ef1388c8fb4dda96325417f6ac8eb4f5a98de247ee5d99 +size 351296801 diff --git a/pytorch_model-00014-of-00082.bin b/pytorch_model-00014-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..56e2d07fccb892c34e4143aad211783ae874beec --- /dev/null +++ b/pytorch_model-00014-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de6baa1ce1272a435d7e32de6b7d83d56a9b37cb3725d62f78487c445fbc46a +size 283116795 diff --git a/pytorch_model-00015-of-00082.bin b/pytorch_model-00015-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..4274f6bef72422a85aa2f4e6d0caa4ec90eac84f --- /dev/null +++ b/pytorch_model-00015-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608634281490aabb385dad884bfea7c9b0bcf4958894c511b7a50f61da760e94 +size 351296801 diff --git a/pytorch_model-00016-of-00082.bin b/pytorch_model-00016-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc38c9e5de5af362359f648a7f9e02dd95a7e8c5 --- /dev/null +++ b/pytorch_model-00016-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa06b238677935c63d81d6accd41907b774a9c46f26ba67995d2d0f3b92781bc +size 283116795 diff --git a/pytorch_model-00017-of-00082.bin b/pytorch_model-00017-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..753dcc3392484796dbb4a2cb492e023287ee97a4 --- /dev/null +++ b/pytorch_model-00017-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6fd68227e993bf18e80f8e2df3c9ea8b477bca6e61d6426b215493c36166ac4 +size 351296801 diff --git a/pytorch_model-00018-of-00082.bin b/pytorch_model-00018-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..0089ecd9c173f126af644a3ddf117b347716cc3e --- /dev/null +++ b/pytorch_model-00018-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc708721cd405826966d9763fecd68f857d71ab485364ab9c744f04b7ff9da7 +size 283116795 diff --git a/pytorch_model-00019-of-00082.bin b/pytorch_model-00019-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..2471e52bcfbba1e006f3c02356d99c1354f9625f --- /dev/null +++ b/pytorch_model-00019-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53cdae1b1e335924e848f3be354adfdd958109bb65ae1003bae8eaf9146067f2 +size 351296801 diff --git a/pytorch_model-00020-of-00082.bin b/pytorch_model-00020-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..f6f6190c29f55ca48c6c80ce314a762f0e3ee2b4 --- /dev/null +++ b/pytorch_model-00020-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530af87a9f43a57c1e6073e9b8511aad9db498eaa9a066cd125e25c96d3ebfa5 +size 283116795 diff --git a/pytorch_model-00021-of-00082.bin b/pytorch_model-00021-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b339825548168e5cd6efe8f6e35407b883a84d83 --- /dev/null +++ b/pytorch_model-00021-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c3f48757a665d6ae19dc5cec7e7f7b6ed7d8b1d750ebae9fbebd7abc9b6acb1 +size 351296865 diff --git a/pytorch_model-00022-of-00082.bin b/pytorch_model-00022-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..5b215c538af17e016e89adad1f7af1ed07c41b24 --- /dev/null +++ b/pytorch_model-00022-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a1b32de9c9bd766428ae4a28b11e98302ddf722e754b81f683aec17341185b +size 283116795 diff --git a/pytorch_model-00023-of-00082.bin b/pytorch_model-00023-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..78952ceb4139e00167f2af43059b17476f465ffc --- /dev/null +++ b/pytorch_model-00023-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd3ef22f8d3336b6f985738cb9c4df7a4ad551a45d107642a1839ca7affcad7 +size 351296865 diff --git a/pytorch_model-00024-of-00082.bin b/pytorch_model-00024-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..205bc26e7e8a862e464aabda5c66facb4d0abb82 --- /dev/null +++ b/pytorch_model-00024-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee436c7827358f1961541481d63e4c3b4df9c7e99e64b400aea6aee38b52b5d6 +size 283116795 diff --git a/pytorch_model-00025-of-00082.bin b/pytorch_model-00025-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b74710c6476d5e48054b823a83dce4443d70ebe --- /dev/null +++ b/pytorch_model-00025-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0d48a5b2b94c79557ab9279e7b43c0da55da51bc4f139dd56f2c728ab2d81f +size 351296865 diff --git a/pytorch_model-00026-of-00082.bin b/pytorch_model-00026-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7675154c6dcc5d10eab53443c06949c290d6782 --- /dev/null +++ b/pytorch_model-00026-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a794049f78d96edf93711302b479890f0ca1b28d6da5c11eb1784f03835c502a +size 283116795 diff --git a/pytorch_model-00027-of-00082.bin b/pytorch_model-00027-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..691e9a2f5d452524fc19eb34061ff1b4e7e98e1c --- /dev/null +++ b/pytorch_model-00027-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:962b44db695f7a26000e9a7caf49312320cbaf39ddc4e80c120fdd45d4fd3360 +size 351296865 diff --git a/pytorch_model-00028-of-00082.bin b/pytorch_model-00028-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..96ca8f67034fb1d8c0eb9c2ea6ad19cb933bb04b --- /dev/null +++ b/pytorch_model-00028-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9266de370f35e7622d1df1c96552865aa5414ec542c828b0a387f1c1847a8bde +size 283116795 diff --git a/pytorch_model-00029-of-00082.bin b/pytorch_model-00029-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..f34dc9556724167efcfe2fa8ced1141a3478b3e1 --- /dev/null +++ b/pytorch_model-00029-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc06957d02ca1a348e91d96412b25f6a6ab725d25954b0f87baad8848ee06c7 +size 351296865 diff --git a/pytorch_model-00030-of-00082.bin b/pytorch_model-00030-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..00d46c4a2c70505f0fec4dd98b46a08439156791 --- /dev/null +++ b/pytorch_model-00030-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31ebfd708b7b70b25cc956420e59a5edf934f288a88080430cf9ef348964a72d +size 283116795 diff --git a/pytorch_model-00031-of-00082.bin b/pytorch_model-00031-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1e3c16dcdbc9e5dbfcf804035119eff37b1382a --- /dev/null +++ b/pytorch_model-00031-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda12c18d68c076b17c5c871a3580512cb84fed34377e2b03e0a6958f336b561 +size 351296865 diff --git a/pytorch_model-00032-of-00082.bin b/pytorch_model-00032-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..30a5224e0952baee3f2d0b8cf9fbbb574247a891 --- /dev/null +++ b/pytorch_model-00032-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafe436c82bb97947d8664f52a1bc5f71c6c89c94398c662db52d925ab828ecb +size 283116795 diff --git a/pytorch_model-00033-of-00082.bin b/pytorch_model-00033-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..fcb40a175ebb84e2591a4126117495e75c5495ae --- /dev/null +++ b/pytorch_model-00033-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580c9cd5134ca7dfe51f68e4fb04d64bc2733fc698fa069fb756642d7cdf879f +size 351296865 diff --git a/pytorch_model-00034-of-00082.bin b/pytorch_model-00034-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..46c7d0a22dc644be829cd08103fe6459fc723576 --- /dev/null +++ b/pytorch_model-00034-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d12adc33d2498cddfd6b7ef25ea834b15dbcfff6efb5bc6056585eacac3add +size 283116795 diff --git a/pytorch_model-00035-of-00082.bin b/pytorch_model-00035-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3f46c8a685b1e5b09909d8ca0602adfc0e86c999 --- /dev/null +++ b/pytorch_model-00035-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399226c84f6377e759d48c3349141fa65d5daa11b3ce6c94693557f5c85742b9 +size 351296865 diff --git a/pytorch_model-00036-of-00082.bin b/pytorch_model-00036-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d6f624e5c0a45906c8f14f33c0462ead2e6e5c54 --- /dev/null +++ b/pytorch_model-00036-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fea7c8efb66840cdad19097321bfd59dfc83a70f343ad651e100f169b66f478 +size 283116795 diff --git a/pytorch_model-00037-of-00082.bin b/pytorch_model-00037-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..16b69e4540efd222e2bc0dc095ed2113ac489d2b --- /dev/null +++ b/pytorch_model-00037-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362b0858936a3a49a43f254fd96b25d8e3cc6ecb5c7a5e7aed22d19aa0169a01 +size 351296865 diff --git a/pytorch_model-00038-of-00082.bin b/pytorch_model-00038-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ea7ddabd1816bb1ffb730cb0f695a39a9e31705 --- /dev/null +++ b/pytorch_model-00038-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aead10cfad1ecf49fbd39a2c77d91ab4e0e7b5b315208ace77c812a8bdf901bd +size 283116795 diff --git a/pytorch_model-00039-of-00082.bin b/pytorch_model-00039-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..e567795f919680407638e8938d4fb141389f65e1 --- /dev/null +++ b/pytorch_model-00039-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8cf0f6453910d54093bd9e48886ece88b6a353a359cbba21ca05f48a8dac1d +size 351296865 diff --git a/pytorch_model-00040-of-00082.bin b/pytorch_model-00040-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ba7e81db4e0eaba1787b2a5f0f287366b42cc4c --- /dev/null +++ b/pytorch_model-00040-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672825fd44e8a05adcf8d61223ad92a02cee961e66ad9d55bc682af183813887 +size 283116795 diff --git a/pytorch_model-00041-of-00082.bin b/pytorch_model-00041-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f4bde136ef978dc5f72ee6d8c71d86d7a2dc991 --- /dev/null +++ b/pytorch_model-00041-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e61ba6b576fb7a78f12cf4fb7d8ca86c08ff38053cebaee9f1e6b7c2062f49 +size 351296865 diff --git a/pytorch_model-00042-of-00082.bin b/pytorch_model-00042-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..67b6c17b2a82b4a8968778148b40257acb1cdcfd --- /dev/null +++ b/pytorch_model-00042-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ac42cbfeb707ac1214a29f224a9c412d49ce909d88e15c1c7cf8ec122dcb2c +size 283116795 diff --git a/pytorch_model-00043-of-00082.bin b/pytorch_model-00043-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..8836fefb119e2e74c1510facc9583501a15d90cd --- /dev/null +++ b/pytorch_model-00043-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecf2ba0a3237dacf1b0b67c8c3e6296bf2671a17c53d412c309ba916980c9ea +size 351296865 diff --git a/pytorch_model-00044-of-00082.bin b/pytorch_model-00044-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b97ed74d982ed474d539a85dd84e9067e85ed8e1 --- /dev/null +++ b/pytorch_model-00044-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f497728b2d23a672f71afab1ad3e031744e309dfffd9324a1dab4a47768dce0f +size 283116795 diff --git a/pytorch_model-00045-of-00082.bin b/pytorch_model-00045-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d067ba1f55f2563fdea5cc5e676598dd2fd13853 --- /dev/null +++ b/pytorch_model-00045-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ba279f7352ff2fe8f9801b4423edbe10a0550af60302a228a486b749207d01 +size 351296865 diff --git a/pytorch_model-00046-of-00082.bin b/pytorch_model-00046-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..49d47d1e6bb93af461b91874f78166f85de23c2d --- /dev/null +++ b/pytorch_model-00046-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480c7a28ae56d67581971aa30562a071b73dbed9dbf2ad8c02d2774e2e680471 +size 283116795 diff --git a/pytorch_model-00047-of-00082.bin b/pytorch_model-00047-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..01def66d8308047ffbc0a2ca5ba3a7794031c4e7 --- /dev/null +++ b/pytorch_model-00047-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184f42b31cac7ec26602951d05745b8743909a7f654084efcd60e614925f1f6f +size 351296865 diff --git a/pytorch_model-00048-of-00082.bin b/pytorch_model-00048-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..c289ee442489dfda1ee4b2270786ea8275e039e8 --- /dev/null +++ b/pytorch_model-00048-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20d5feca6facc0083fa6f562955cfc1ba2c2b785c24ef6475219e5ffec26f3a +size 283116795 diff --git a/pytorch_model-00049-of-00082.bin b/pytorch_model-00049-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecf858ea419dabc8b3ac0bf86d14fb27dd1d84c8 --- /dev/null +++ b/pytorch_model-00049-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d441e75614cbf0de71ee9c79755a835b8d3429171dcfedd5b6908fb70b375fe4 +size 351296865 diff --git a/pytorch_model-00050-of-00082.bin b/pytorch_model-00050-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..036230a78484b3375d41b559479dbec36a8b56c3 --- /dev/null +++ b/pytorch_model-00050-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e755bb9bbb5a6af7f9bc719a0e3391bf50835bd7e9543842c7986d7ac3a3b5a8 +size 283116795 diff --git a/pytorch_model-00051-of-00082.bin b/pytorch_model-00051-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..51eeca1540e0abb706a1280ba244628dad3423ad --- /dev/null +++ b/pytorch_model-00051-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75193138c2818f2ec0409c564dc15e34169a7d1aec17ff796a001bd7d42c6dba +size 351296865 diff --git a/pytorch_model-00052-of-00082.bin b/pytorch_model-00052-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e08939ed5bf889e04cfd8b16ace6df441cb061f --- /dev/null +++ b/pytorch_model-00052-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de8f576779c05d6b47349e19eca90f37ba0284ef443fe40c3f6dfe1b1bcd07a +size 283116795 diff --git a/pytorch_model-00053-of-00082.bin b/pytorch_model-00053-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..297aad43b440466d85bd2e40a1731c2c7f4d4708 --- /dev/null +++ b/pytorch_model-00053-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc296a4027776784a9026fd29e90a07b97259bdabab318b3cf06a738807a6fc9 +size 351296865 diff --git a/pytorch_model-00054-of-00082.bin b/pytorch_model-00054-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..2d09d19133a620d254e737bfdef341948069aec0 --- /dev/null +++ b/pytorch_model-00054-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bec617293a013d9da1b9b2fabac1e8a20d3ae093ed8f92ae517129ae623a9fd +size 283116795 diff --git a/pytorch_model-00055-of-00082.bin b/pytorch_model-00055-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..20b3ea2a7968fb0f1ba0484751844581cb6ae943 --- /dev/null +++ b/pytorch_model-00055-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d788e9b160f5f76041f36680fa9c1fc7641482210a4e88ffbaf44f4a3008c53 +size 351296865 diff --git a/pytorch_model-00056-of-00082.bin b/pytorch_model-00056-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..366178115d1606a9895e78657f051408e6bc3230 --- /dev/null +++ b/pytorch_model-00056-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc21a8e652e3191b850c79f08251d132cd065acf8a79c33e699b037b2735086 +size 283116795 diff --git a/pytorch_model-00057-of-00082.bin b/pytorch_model-00057-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..dda6f5485f00baa0b1b93c97a6b749e412f0bfb8 --- /dev/null +++ b/pytorch_model-00057-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5059c1060712e479a1afe10da78bc0cbe7df0e638d9af212286a23e3932c0f79 +size 351296865 diff --git a/pytorch_model-00058-of-00082.bin b/pytorch_model-00058-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..166d70f8635b98003e155e2abd8512129287fe88 --- /dev/null +++ b/pytorch_model-00058-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c5d7f6dfa87fd6b951772a831072c3317fa0b3f7c13e50a3d78056504cbc07b +size 283116795 diff --git a/pytorch_model-00059-of-00082.bin b/pytorch_model-00059-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd060ebc22276f7330e88737f5bbd19d4d338460 --- /dev/null +++ b/pytorch_model-00059-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbad244a6a3e19c6832a65c91949ba7c8b6777e47307ee91746d55bce72e886d +size 351296865 diff --git a/pytorch_model-00060-of-00082.bin b/pytorch_model-00060-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb9d64fa8b491ab2cedafe52d0d83d30b366f909 --- /dev/null +++ b/pytorch_model-00060-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eeba531a64936ec7ad18a1ecfac16d7d7da5a1dbffeccac10c41596f91a0482 +size 283116795 diff --git a/pytorch_model-00061-of-00082.bin b/pytorch_model-00061-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..903c869cf49cdedec078e993c6f5347a2518e2f3 --- /dev/null +++ b/pytorch_model-00061-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7af02c354826a45ac84597c0f0fd5d48c7047e423df6c89c5d2b081acf7d763 +size 351296865 diff --git a/pytorch_model-00062-of-00082.bin b/pytorch_model-00062-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c107b68b5143d8bebe9e5570b3890f5ea0e1a86 --- /dev/null +++ b/pytorch_model-00062-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a202eba0002ffd5771949b45d37788b6393b8b1c75d14eb3bd04856d7da063a5 +size 283116795 diff --git a/pytorch_model-00063-of-00082.bin b/pytorch_model-00063-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..591d22ead641271e8e9ca459f2d4a43700d2288f --- /dev/null +++ b/pytorch_model-00063-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcfc260a55ec452059d11a2dc2af3e20c1f393e97be1a1fee0ca4ebc727c9234 +size 351296865 diff --git a/pytorch_model-00064-of-00082.bin b/pytorch_model-00064-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..50cc2c8a65bd2c63eeb65d1852bda4d515931417 --- /dev/null +++ b/pytorch_model-00064-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cffc895693bd631d86ac0348f64e8783337ee67f1d0ed23f04463a8eab0eee +size 283116795 diff --git a/pytorch_model-00065-of-00082.bin b/pytorch_model-00065-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..96e4357d92c668fd0e908c20ef2c4151a76a97f3 --- /dev/null +++ b/pytorch_model-00065-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a89ca70b320f0d7f01db5c23298a562bb1d1632be53f6139f96b9904ccd83bd +size 351296865 diff --git a/pytorch_model-00066-of-00082.bin b/pytorch_model-00066-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..4093b50b08d602e2c7a3ee507216d0c92262df06 --- /dev/null +++ b/pytorch_model-00066-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d887baa17487b1ee299a8ccda307a1c605faf927b590a15b261a0913b27292e5 +size 283116795 diff --git a/pytorch_model-00067-of-00082.bin b/pytorch_model-00067-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..079c31840549cd708c6484ce903d7c1c0453dcd9 --- /dev/null +++ b/pytorch_model-00067-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7b2152a7aa53cb30535193e51326d229ee790c4b9af9062b08320015fc8087 +size 351296865 diff --git a/pytorch_model-00068-of-00082.bin b/pytorch_model-00068-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..0be16d6de37675531874b06fd6f1e8b7db373730 --- /dev/null +++ b/pytorch_model-00068-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d3ec873c65d5caf8b3ef9b42de713903f604feff1ab5f720e6e652d509bb18 +size 283116795 diff --git a/pytorch_model-00069-of-00082.bin b/pytorch_model-00069-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b06c3fd18a7d1f754e7a2caca543d6f992d78876 --- /dev/null +++ b/pytorch_model-00069-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98bb4563f2c965f7c599d2b317619eb7a3b6c8f3dc176dc2c2a98418f4c1b0f8 +size 351296865 diff --git a/pytorch_model-00070-of-00082.bin b/pytorch_model-00070-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc716cc2ec3321a9bd0f6e360bc389bb15814bbf --- /dev/null +++ b/pytorch_model-00070-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cf6667c3c971af861651e06a106c65c9116a4f5174c6c2cc15614b7179a980 +size 283116795 diff --git a/pytorch_model-00071-of-00082.bin b/pytorch_model-00071-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7c9492d0ec2a6a9e529d93f31ef2b48c64e76f4 --- /dev/null +++ b/pytorch_model-00071-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a02ccb65ee79e8d1669da305a2cb0fb257bbee15538d4a31195810447a5b925 +size 351296865 diff --git a/pytorch_model-00072-of-00082.bin b/pytorch_model-00072-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..315b975f0fd276158612542316e4a24bc091f33f --- /dev/null +++ b/pytorch_model-00072-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f896893f2be1dab7adcf62043080d6d4d637e765f2d9a95fa1dcdc4a283fa06 +size 283116795 diff --git a/pytorch_model-00073-of-00082.bin b/pytorch_model-00073-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b279b845dad857ea3d78a306c87c73d6f183a70 --- /dev/null +++ b/pytorch_model-00073-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b730475f892ed1ea9fd89e9ece095ab885155e36885a06980ebe1803b69b6b8d +size 351296865 diff --git a/pytorch_model-00074-of-00082.bin b/pytorch_model-00074-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..68fdbf63d22dead1c27b7cb7a4038bf0961b9ad9 --- /dev/null +++ b/pytorch_model-00074-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f100af49f0ea6110c8992814b7a655e2d53c37bf5de3365dd67b374361d0522e +size 283116795 diff --git a/pytorch_model-00075-of-00082.bin b/pytorch_model-00075-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2ab29ef00be972f6b9f5d3920c306c07f1b3331 --- /dev/null +++ b/pytorch_model-00075-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1e1ad333efd3085555f1d76029402af4ee948f532297c82102622e97387100 +size 351296865 diff --git a/pytorch_model-00076-of-00082.bin b/pytorch_model-00076-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a3e6dab07b5b05ff902e6fe2561ff4e29f8fe55a --- /dev/null +++ b/pytorch_model-00076-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33d38bb1953236a4bf75db7080e396298bf49e01c58378e83311652494c1434 +size 283116795 diff --git a/pytorch_model-00077-of-00082.bin b/pytorch_model-00077-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a9bb69f55fe78c0bc482d81132d4f18a32c7a3d1 --- /dev/null +++ b/pytorch_model-00077-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:004ad2b74ba10e5f63517e3078d6613808a07843c68a06ca0376b84d6d8ea25c +size 351296865 diff --git a/pytorch_model-00078-of-00082.bin b/pytorch_model-00078-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..adec4e8208cfbfe2561ff417f2118b7a0b7ce9b8 --- /dev/null +++ b/pytorch_model-00078-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9dd815d6c6529b9fd72059d4b6da7addfe33eb9767af3317f1e84c7a974f74c +size 283116795 diff --git a/pytorch_model-00079-of-00082.bin b/pytorch_model-00079-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..e82b587f5f9a54c6cf0a574c749ed18b6c16aa0d --- /dev/null +++ b/pytorch_model-00079-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60cfdfc6b6e499c1d3669dcf5783d83d52b24e27693e0a0710b574299575a97a +size 351296865 diff --git a/pytorch_model-00080-of-00082.bin b/pytorch_model-00080-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9b14efd5c45085569d6155f348322317f289466 --- /dev/null +++ b/pytorch_model-00080-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0cb8409149d3e34a61ba5701af3d1a42ddf682ca2fca5e6e4dcb8d55f33fe89 +size 283116795 diff --git a/pytorch_model-00081-of-00082.bin b/pytorch_model-00081-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d24a4666fff86502a7fc15ad21759b95138b8ad6 --- /dev/null +++ b/pytorch_model-00081-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e63093bdd6f0af43f4a1db4b1a65424f5da9a3495faa55ab580c190dd724d21 +size 141590301 diff --git a/pytorch_model-00082-of-00082.bin b/pytorch_model-00082-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..83124295833c3204efe19d01273aca1811d73825 --- /dev/null +++ b/pytorch_model-00082-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6213bf1a1cb30fad2e3d17ed7478f68c1ca39d8bda4039807f551b850155d90 +size 327680938 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000000000000000000000000000000000000..e684cedb1a653453ef5bec1df2994064d057ee48 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 26031738880 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00082-of-00082.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00082.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00082.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00082.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00082.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00022-of-00082.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00022-of-00082.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00024-of-00082.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00024-of-00082.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00026-of-00082.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00026-of-00082.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00028-of-00082.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00028-of-00082.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00030-of-00082.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00030-of-00082.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00032-of-00082.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00032-of-00082.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00034-of-00082.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00034-of-00082.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00036-of-00082.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00036-of-00082.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00038-of-00082.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00038-of-00082.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00040-of-00082.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00040-of-00082.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00006-of-00082.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00006-of-00082.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00042-of-00082.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00042-of-00082.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00044-of-00082.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00044-of-00082.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00046-of-00082.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00046-of-00082.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00048-of-00082.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00048-of-00082.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00050-of-00082.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00050-of-00082.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00052-of-00082.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00052-of-00082.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00054-of-00082.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00054-of-00082.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00056-of-00082.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00056-of-00082.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00058-of-00082.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00058-of-00082.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00060-of-00082.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00060-of-00082.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00008-of-00082.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00008-of-00082.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00062-of-00082.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00062-of-00082.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00064-of-00082.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00064-of-00082.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00066-of-00082.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00066-of-00082.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00068-of-00082.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00068-of-00082.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00070-of-00082.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00070-of-00082.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00072-of-00082.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00072-of-00082.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00074-of-00082.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00074-of-00082.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00076-of-00082.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00076-of-00082.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00078-of-00082.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00078-of-00082.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00081-of-00082.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00080-of-00082.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00080-of-00082.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00081-of-00082.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00081-of-00082.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00010-of-00082.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00010-of-00082.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00012-of-00082.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00012-of-00082.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00014-of-00082.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00014-of-00082.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00016-of-00082.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00016-of-00082.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00018-of-00082.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00018-of-00082.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00020-of-00082.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00020-of-00082.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.norm.weight": "pytorch_model-00081-of-00082.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..451134b2ddc2e78555d1e857518c54b4bdc2e87d --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9e72adb60a1e9065645bd61fb8fa22d3423037b5 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +}