diff --git a/model/backbone.pt b/model/backbone.pt new file mode 100644 index 0000000000000000000000000000000000000000..8173ff09689bfdb8119303ca3ec0601af1702d61 --- /dev/null +++ b/model/backbone.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14f311274f69ff3f06722c5db2279c69a4d40038e12051d56446a77859d3232 +size 2322241 diff --git a/model/config.json b/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9712ab9b7fa623f711ac44dd65b5794348f0e5be --- /dev/null +++ b/model/config.json @@ -0,0 +1,158 @@ +{ + "config": { + "block_size": 128, + "n_layer": 2, + "n_head": 4, + "n_embd": 256, + "dropout": 0.1, + "num_moes": 6, + "num_experts": 8, + "batch_size": 32, + "max_iters": 500, + "eval_interval": 50, + "eval_iters": 20, + "lr": 0.0003, + "data_file": "hamlet.txt", + "model_dir": "model" + }, + "vocab_size": 67, + "step": 500, + "stoi": { + "\n": 0, + " ": 1, + "!": 2, + "\"": 3, + "&": 4, + "'": 5, + "(": 6, + ")": 7, + ",": 8, + "-": 9, + ".": 10, + "1": 11, + ":": 12, + ";": 13, + "?": 14, + "A": 15, + "B": 16, + "C": 17, + "D": 18, + "E": 19, + "F": 20, + "G": 21, + "H": 22, + "I": 23, + "J": 24, + "K": 25, + "L": 26, + "M": 27, + "N": 28, + "O": 29, + "P": 30, + "Q": 31, + "R": 32, + "S": 33, + "T": 34, + "U": 35, + "V": 36, + "W": 37, + "Y": 38, + "[": 39, + "]": 40, + "a": 41, + "b": 42, + "c": 43, + "d": 44, + "e": 45, + "f": 46, + "g": 47, + "h": 48, + "i": 49, + "j": 50, + "k": 51, + "l": 52, + "m": 53, + "n": 54, + "o": 55, + "p": 56, + "q": 57, + "r": 58, + "s": 59, + "t": 60, + "u": 61, + "v": 62, + "w": 63, + "x": 64, + "y": 65, + "z": 66 + }, + "itos": { + "0": "\n", + "1": " ", + "2": "!", + "3": "\"", + "4": "&", + "5": "'", + "6": "(", + "7": ")", + "8": ",", + "9": "-", + "10": ".", + "11": "1", + "12": ":", + "13": ";", + "14": "?", + "15": "A", + "16": "B", + "17": "C", + "18": "D", + "19": "E", + "20": "F", + "21": "G", + "22": "H", + "23": "I", + "24": "J", + "25": "K", + "26": "L", + "27": "M", + "28": "N", + "29": "O", + "30": "P", + "31": "Q", + "32": "R", + "33": "S", + "34": "T", + "35": "U", + "36": "V", + "37": "W", + "38": "Y", + "39": "[", + "40": "]", + "41": "a", + "42": "b", + "43": "c", + "44": "d", + "45": "e", + "46": "f", + "47": "g", + "48": "h", + "49": "i", + "50": "j", + "51": "k", + "52": "l", + "53": "m", + "54": "n", + "55": "o", + "56": "p", + "57": "q", + "58": "r", + "59": "s", + "60": "t", + "61": "u", + "62": "v", + "63": "w", + "64": "x", + "65": "y", + "66": "z" + } +} \ No newline at end of file diff --git a/model/layer_01_main_router.pt b/model/layer_01_main_router.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba10dde890e05e657be3f644d367610781e2d319 --- /dev/null +++ b/model/layer_01_main_router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc4803c65495a8d77e08bbe1d62ac1136c314602ba2a47045b3abdd13e8a86c +size 7876 diff --git a/model/layer_01_moe_expert_001/model_001.pt b/model/layer_01_moe_expert_001/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f01311e0bca8780acbfc452d20d0e9ffcb634c0 --- /dev/null +++ b/model/layer_01_moe_expert_001/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114b7753a3bf94e2db56f3d91be012e15f8bd962ebb5a223f483cc73eb679b87 +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_002.pt b/model/layer_01_moe_expert_001/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..8927aa56da1279f6d7464cababa1b817928997d0 --- /dev/null +++ b/model/layer_01_moe_expert_001/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bd91795ea832e2d96ffd398d8a7018a8e8a27aebfd6e6c8088996b1b5c4da3 +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_003.pt b/model/layer_01_moe_expert_001/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..584346b676db88b78170c07bcdbb258e1d7a6532 --- /dev/null +++ b/model/layer_01_moe_expert_001/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f2b8d4f745224c99c89b1b5c96f78271051e9578c0b07c34579657da49c01f +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_004.pt b/model/layer_01_moe_expert_001/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..5971f0c4e850dbce9223ba534b34926d140b0f9a --- /dev/null +++ b/model/layer_01_moe_expert_001/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d936b1c83a8229c36032bd2d6d60b92b34fc8ab96305eaa361fc23cb1113e9 +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_005.pt b/model/layer_01_moe_expert_001/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ab22dafc9880fedaddb7163838477f688cb0142 --- /dev/null +++ b/model/layer_01_moe_expert_001/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4e35cd1b9d6cdeaa6feec76ed2f65aff45da24dc5c2480c0272a4ba19e817f +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_006.pt b/model/layer_01_moe_expert_001/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..d11be7816a87e153f94de27ad5d348caf01f317d --- /dev/null +++ b/model/layer_01_moe_expert_001/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8aac1c7afb24e2e46077cc0ec6d3fd12863eb3cee8ca2392f4f9bbed149eb7 +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_007.pt b/model/layer_01_moe_expert_001/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..5fbcf3dcbcf1046e2de03a5e97045b07c609ea72 --- /dev/null +++ b/model/layer_01_moe_expert_001/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfeb19445b93c0afb05e1a82150a83d6dd8feae22a7fe24125d01f45d3160920 +size 2104881 diff --git a/model/layer_01_moe_expert_001/model_008.pt b/model/layer_01_moe_expert_001/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6e80619b1656894a1ec5ff3b00465d63c16dc57 --- /dev/null +++ b/model/layer_01_moe_expert_001/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdb7fad20a47de1e9148d68b39c737f11eca894066fd375c8adb9fd32470a4c +size 2104881 diff --git a/model/layer_01_moe_expert_001/router.pt b/model/layer_01_moe_expert_001/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..48d287f24e6ecfcc8775ba1ec4a3e253b8c04176 --- /dev/null +++ b/model/layer_01_moe_expert_001/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3916190906b36a1dc8f6eabebcbf6c3ad7975657c3a395a80ffd18dcaeac72 +size 9762 diff --git a/model/layer_01_moe_expert_002/model_001.pt b/model/layer_01_moe_expert_002/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..64301f61b3ca5ad840af1b011d59ebc6165aad7a --- /dev/null +++ b/model/layer_01_moe_expert_002/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6665fc870417fa735b533eebf2e56c0a7fa9da5b3680dd18b6f59cd2fae3e6b8 +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_002.pt b/model/layer_01_moe_expert_002/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..2146ac0db0e506af804ed739cedab0fe2c4440dc --- /dev/null +++ b/model/layer_01_moe_expert_002/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0161939d4709ccfb1fc84f243300d8bc79136f834f4bf53298f25752529eb8fd +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_003.pt b/model/layer_01_moe_expert_002/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..921e2708322a0b58b49ece127a0bcf5404db80db --- /dev/null +++ b/model/layer_01_moe_expert_002/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b0358fad9b1c03f5ff52bfe19a8187d933442a18da50f9dd6587f01a5b6d17 +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_004.pt b/model/layer_01_moe_expert_002/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..45ceabc7308531821253bcd5f8f30cef10266fea --- /dev/null +++ b/model/layer_01_moe_expert_002/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6127d6e715972db1da1389edae44308b286b3741af73a13316916c1cccdbaee +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_005.pt b/model/layer_01_moe_expert_002/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb817f246d44ccf7fcb770cd35ddce5e69c0b998 --- /dev/null +++ b/model/layer_01_moe_expert_002/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c2a712da9c4c26419d692b48a54e88aa7db8809b65a5d774cbcdd740d756db +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_006.pt b/model/layer_01_moe_expert_002/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d1ac13f133770cdca8fc502c96de22f6a02b86b --- /dev/null +++ b/model/layer_01_moe_expert_002/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8baaa6b100a00e395407aadae45289d1324eee3def44c4c56f31117fe2f0a770 +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_007.pt b/model/layer_01_moe_expert_002/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..51c6c906d2ab105be1a8741637925e76a6da244e --- /dev/null +++ b/model/layer_01_moe_expert_002/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e4d9de453dcca691c5f9656558f2e26032f34e835640c657e350b36b61ba50 +size 2104881 diff --git a/model/layer_01_moe_expert_002/model_008.pt b/model/layer_01_moe_expert_002/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4582a420408c19f956ab310d5b0c807c9311bbf --- /dev/null +++ b/model/layer_01_moe_expert_002/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7bebae9d8814ee53ab9729f18a68e2e05e93d6d7057e1d4546084cf264f93ee +size 2104881 diff --git a/model/layer_01_moe_expert_002/router.pt b/model/layer_01_moe_expert_002/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..95db7e29f367d5e311d560542242184a4593bdbd --- /dev/null +++ b/model/layer_01_moe_expert_002/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff877d6965348142d4bf0e86a64e3217459cf810fdaf860fddbcd975e8e5b86b +size 9762 diff --git a/model/layer_01_moe_expert_003/model_001.pt b/model/layer_01_moe_expert_003/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..d894ad74a5058b05e587b0b86f4ea75451e06579 --- /dev/null +++ b/model/layer_01_moe_expert_003/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27e9f596512a3e624205dbde10031b47c23bcce52e75ca893c93fb7d19bcb4d +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_002.pt b/model/layer_01_moe_expert_003/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c1ccc540ca2387ef4c489d7c4e0bded22e99bc0 --- /dev/null +++ b/model/layer_01_moe_expert_003/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce623d27c15f1a555e9718a93469d17a448cc87001439d4d22e2e5ea62b47d7 +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_003.pt b/model/layer_01_moe_expert_003/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c705ce00b2df15e2cd062d6bdf13c3394cf678e --- /dev/null +++ b/model/layer_01_moe_expert_003/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9232187d4a5382b64e18a51f40e210cd1818dd22c5fa14a2dc8fde12d30984 +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_004.pt b/model/layer_01_moe_expert_003/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..db0e1a98cd6c9e33374f14ac2d1616dcd1b00de0 --- /dev/null +++ b/model/layer_01_moe_expert_003/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:518a9235d19b3ef4e8a2ec8f8a5a97ff586df52bfc3748702ae86c826770db4f +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_005.pt b/model/layer_01_moe_expert_003/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..32047435af9465f03402c8fef992c69c4a114e7b --- /dev/null +++ b/model/layer_01_moe_expert_003/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35422170b4f6ac417ce2b1df1e4548c678bdc5e4969ff3f7266ed9c97f47dc80 +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_006.pt b/model/layer_01_moe_expert_003/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..45cd5644575f780b21ae34edd807776ec0498561 --- /dev/null +++ b/model/layer_01_moe_expert_003/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91b87c4971c6b394c8664db8a8fba0cef2e438e964bfb4283fae6c2c6e1252a +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_007.pt b/model/layer_01_moe_expert_003/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..08908965d9e63592d73ade4477d48b1e9b420444 --- /dev/null +++ b/model/layer_01_moe_expert_003/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff1ec132722af4fc7f30b5db9c744268c09e7c4bc9f2cd855a72deec00b1d00f +size 2104881 diff --git a/model/layer_01_moe_expert_003/model_008.pt b/model/layer_01_moe_expert_003/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..941b54cc024aad689111c9ba5eec2a38d4c7b26a --- /dev/null +++ b/model/layer_01_moe_expert_003/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555d2114d7bd519465a1e4adf355de0bff3b1ed138e9873760bcc55e650f7732 +size 2104881 diff --git a/model/layer_01_moe_expert_003/router.pt b/model/layer_01_moe_expert_003/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..a93c178d2fb0338860c574a88b1fbbafd527fc88 --- /dev/null +++ b/model/layer_01_moe_expert_003/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af3f77b22f11f620388c7b2294ccdd80ea950ffb80fa221f8b62ba292656861 +size 9762 diff --git a/model/layer_01_moe_expert_004/model_001.pt b/model/layer_01_moe_expert_004/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..11607e1e56fc84bb77e50c748b183aedda8ad93a --- /dev/null +++ b/model/layer_01_moe_expert_004/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfa44526869e13728f27d122ed32b19818f6a7af8c1881cb3bf7fc850a2566e +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_002.pt b/model/layer_01_moe_expert_004/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc141fbfb159e7205d3e9504ff5df59d3211daa4 --- /dev/null +++ b/model/layer_01_moe_expert_004/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5856ed69a4512d58b9c19409f428f24ac2c9b5817c49bb2fd35da3a443276729 +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_003.pt b/model/layer_01_moe_expert_004/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..83fefca56d498d7db2717e712b44818894d67f8f --- /dev/null +++ b/model/layer_01_moe_expert_004/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28eef58ff4522c7bfaae14a459bc860519b9c4aef6abe15d2d5695d7d1f954cc +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_004.pt b/model/layer_01_moe_expert_004/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b6a89bd2337a0b78c8fdafcc229351213b00574 --- /dev/null +++ b/model/layer_01_moe_expert_004/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a20fe86108c4196bf76936386e4eed81ca1b25493413c05b91cde26fe759a0fd +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_005.pt b/model/layer_01_moe_expert_004/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..b494c8f83859e2742a45cc2ce4167491e4dbc2ab --- /dev/null +++ b/model/layer_01_moe_expert_004/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7137bfe0563d259f3bab97c65c5d2664325eaa6c3a21fd4af0abc69d7c237b5d +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_006.pt b/model/layer_01_moe_expert_004/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..19670f9d5fe2f667557fdfc533fd5b925ca63f72 --- /dev/null +++ b/model/layer_01_moe_expert_004/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac98a8a0924e1ed83f55ae9d3f372f3509a10de35aeccb4a5151b8a5fc37242 +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_007.pt b/model/layer_01_moe_expert_004/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cef2ae25638b033e7a6e90773ea67f58cb87eb7 --- /dev/null +++ b/model/layer_01_moe_expert_004/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc727bdb594a4d91d5ed4b93bcc5f7127b59e664fcf9df584de0fd1e74b96898 +size 2104881 diff --git a/model/layer_01_moe_expert_004/model_008.pt b/model/layer_01_moe_expert_004/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ecef4387b8688975abe749bf27f39f928ae2cf9 --- /dev/null +++ b/model/layer_01_moe_expert_004/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e893a286f95d30c556af59ed4bffaf77f8cab15bb7be9d5af5f7940adc613b +size 2104881 diff --git a/model/layer_01_moe_expert_004/router.pt b/model/layer_01_moe_expert_004/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..9539ccba8b0a58be74ed568cfe90ee01eece98af --- /dev/null +++ b/model/layer_01_moe_expert_004/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668147605eae36465c25d5863fe87fe0ef05e17c8ebd0c0b9bd971eca18ff650 +size 9762 diff --git a/model/layer_01_moe_expert_005/model_001.pt b/model/layer_01_moe_expert_005/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7867fa946004e04bb6dbf756b6b84f1d3a26dce --- /dev/null +++ b/model/layer_01_moe_expert_005/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a1d0348ce078ed41ad04ad00a5725256e7236ac2f4d3c67cc363298aa773b4e +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_002.pt b/model/layer_01_moe_expert_005/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..396b84abbdc93f37ed6c53677c2da76a62dbd2b7 --- /dev/null +++ b/model/layer_01_moe_expert_005/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0920db81b9187797f8b9f7c6d36ce826d09caca2bb3aed91c6712d2755f542e +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_003.pt b/model/layer_01_moe_expert_005/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..1082aa0324e6fc9cd14a949c5d5fb47ecd5c19ff --- /dev/null +++ b/model/layer_01_moe_expert_005/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7331974b3d1f5374064b0c7b2ed77b3e1cc8995c18aaee7106c2164ecef9b71b +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_004.pt b/model/layer_01_moe_expert_005/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c8f1ed8702d146328171cada2397b11d2cf59e5 --- /dev/null +++ b/model/layer_01_moe_expert_005/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12bc8747c96d40bc2c492de3ccc543e3f97a6c5899cdcc5b8bd0409b37ef357 +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_005.pt b/model/layer_01_moe_expert_005/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad4e364ff1b5438a3420352889bb5780037c79df --- /dev/null +++ b/model/layer_01_moe_expert_005/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2ec04f332479ceefc6780c365bd799da239b451a399e54d9fe23757a89e081 +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_006.pt b/model/layer_01_moe_expert_005/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..b17a04bb6ed4da337282909280505f5bd03d0b7f --- /dev/null +++ b/model/layer_01_moe_expert_005/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2f03e2bfeb6a1eab173aad761da2b48ca037def1ba1649d6f41c93ce101f31 +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_007.pt b/model/layer_01_moe_expert_005/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..08b0c6645c4a86541314546c75d5cdbdc4990f4e --- /dev/null +++ b/model/layer_01_moe_expert_005/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb3850cc3e37f20c245c982ce24fb2c2d477c63b01900fb980c2af61cc60cdb +size 2104881 diff --git a/model/layer_01_moe_expert_005/model_008.pt b/model/layer_01_moe_expert_005/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..e30c54b7784d240f195dc26255792d1e95298358 --- /dev/null +++ b/model/layer_01_moe_expert_005/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19679e22d959ad56b73545822374214accada6fc8efa84db13c9505123b110f5 +size 2104881 diff --git a/model/layer_01_moe_expert_005/router.pt b/model/layer_01_moe_expert_005/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..89b6fb90fc49de2b7ecbbac4aa2d1a486533c958 --- /dev/null +++ b/model/layer_01_moe_expert_005/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48182bbd38ea1d96ac1f919ac10db7fde53151756beae3eb8c88f6998ff3c1e +size 9762 diff --git a/model/layer_01_moe_expert_006/model_001.pt b/model/layer_01_moe_expert_006/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..429f5fdcc5dc53c63f85cda284c83dd1a73f9e49 --- /dev/null +++ b/model/layer_01_moe_expert_006/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e90c20e2018258584dde8679f973a58051285cf326723e5e3d6188ccb920a32 +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_002.pt b/model/layer_01_moe_expert_006/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3b94e5d55d6f376c15df7be9a1ba6c2262f4462 --- /dev/null +++ b/model/layer_01_moe_expert_006/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4279cdec0065b03c6b6c4325ae68b76aac95156625e1bc74349e7e07dd028cab +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_003.pt b/model/layer_01_moe_expert_006/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..eeceab28e9b31413e15a197469de4e7de835f8fb --- /dev/null +++ b/model/layer_01_moe_expert_006/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39db5e64893bf960fb129e0aa4e43611557f85a3c1902b2568f413fe7e4497b +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_004.pt b/model/layer_01_moe_expert_006/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..3343990cb8774c97386fa36eeb7406e33de18aed --- /dev/null +++ b/model/layer_01_moe_expert_006/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e46e9d04182aae910696e1f8852010b5006e791f7c2949009e233c328a2613e8 +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_005.pt b/model/layer_01_moe_expert_006/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad6f0be68f1a37abae27857ae6f98db3f14b216f --- /dev/null +++ b/model/layer_01_moe_expert_006/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874a6df1bec18d8ddfbc74eb16b44c5f6521fca45916356d3e00f5765eb508d9 +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_006.pt b/model/layer_01_moe_expert_006/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..9574c3f32a96472a1aa055d14426210eeec42093 --- /dev/null +++ b/model/layer_01_moe_expert_006/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6615dbbf195de74a795e0545b34f94a442b629b55e2fb619e3979f8c0b93415 +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_007.pt b/model/layer_01_moe_expert_006/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..42820bb4e44e7f4b74a09f6ddcfe28ba7dd8a7fe --- /dev/null +++ b/model/layer_01_moe_expert_006/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fded3ff18c138e2b22b4a5fd4ae2302c6fbc9e3ab4460611ce6455cccdbb1d2 +size 2104881 diff --git a/model/layer_01_moe_expert_006/model_008.pt b/model/layer_01_moe_expert_006/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..4eccd15478305e11a42595c2aa352ae3c1be839b --- /dev/null +++ b/model/layer_01_moe_expert_006/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f9945a88794f650e55fa3b5aab3303f290062a7cb84304af7b9473cae255b0 +size 2104881 diff --git a/model/layer_01_moe_expert_006/router.pt b/model/layer_01_moe_expert_006/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..985a992e25fa6cf333796db8932ed48f03a0a82a --- /dev/null +++ b/model/layer_01_moe_expert_006/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4845c0a2188c0e9ce8e3b746b846e26e6f37ea570032b5d25bd6ae369675793e +size 9762 diff --git a/model/layer_02_main_router.pt b/model/layer_02_main_router.pt new file mode 100644 index 0000000000000000000000000000000000000000..74dd5d0505096d79065fc4741c10b7553466b3e7 --- /dev/null +++ b/model/layer_02_main_router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db769615ebf5c3a7d08263791c038af05a84e38738a8aa5c223974fe73de70c6 +size 7876 diff --git a/model/layer_02_moe_expert_001/model_001.pt b/model/layer_02_moe_expert_001/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..127a9b2474ca32c95b833fa4846920b899b9df51 --- /dev/null +++ b/model/layer_02_moe_expert_001/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baaaa17a2ddeb17e3bd047b790f68a24367e02a16d84b39bdc82e8dca94a625a +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_002.pt b/model/layer_02_moe_expert_001/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..e315a48b47ea0015607cc810084db24ee4a071cb --- /dev/null +++ b/model/layer_02_moe_expert_001/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d44ea64112abd052726ad3fc00df52569d6f3d40d1c3967ebbd5ebb9c2fb6c1f +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_003.pt b/model/layer_02_moe_expert_001/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f7f531374489605e645731b8e4735e27a52efd7 --- /dev/null +++ b/model/layer_02_moe_expert_001/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98850b2f332180f70f682fa8bddafbb1b0e9551ea9b23b471eef232dc8882fa0 +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_004.pt b/model/layer_02_moe_expert_001/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2eba37e635d7e4b0531a582fabd7e4c48ed4a91 --- /dev/null +++ b/model/layer_02_moe_expert_001/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33dab275ca41897fdd196589046bae469521cc1983a0b81847fbfaf576151318 +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_005.pt b/model/layer_02_moe_expert_001/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..f10b2443391bcefbf876b55001c45473e3c4aa1b --- /dev/null +++ b/model/layer_02_moe_expert_001/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5287d70d208127b45646b77d785f467e1ecd838906c0d79b644adc8ed7228311 +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_006.pt b/model/layer_02_moe_expert_001/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..4804111d45c0e7c96e51b17c58923f14d25aa142 --- /dev/null +++ b/model/layer_02_moe_expert_001/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2dc0f55aa4844accdd9e74491fe1c8566dbfb65096da60d5091baae27e05db +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_007.pt b/model/layer_02_moe_expert_001/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..1637c80f279c0bd33e37f5ea90031deff6615ce0 --- /dev/null +++ b/model/layer_02_moe_expert_001/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e47dc3959b4303db40896baa50561268a9dfb585ab8e74afe4bbf6ec1ee1142a +size 2104881 diff --git a/model/layer_02_moe_expert_001/model_008.pt b/model/layer_02_moe_expert_001/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..7202592ad70a737eb9a9339eda2c821906c68eac --- /dev/null +++ b/model/layer_02_moe_expert_001/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9662547c583a337b97523ec884dbca971b5adb1bf438977ae2ccd22005b5aea +size 2104881 diff --git a/model/layer_02_moe_expert_001/router.pt b/model/layer_02_moe_expert_001/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec9701a65d6b3f3da73957acff5c5b9bb25d657f --- /dev/null +++ b/model/layer_02_moe_expert_001/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7039aae648f566e780cab0fca042570e9f5079da971d6b6ac3b0eb940d4347c0 +size 9762 diff --git a/model/layer_02_moe_expert_002/model_001.pt b/model/layer_02_moe_expert_002/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb8f919fe90b7f00032d70588fffd6555bc6c1bb --- /dev/null +++ b/model/layer_02_moe_expert_002/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bea0f9f916fe57fe66040df32636900eeaf2fd5b3e71005818cd2672f51c71 +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_002.pt b/model/layer_02_moe_expert_002/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cfa5185c64bc5ca4ea25e44df0f724a14c9fd60 --- /dev/null +++ b/model/layer_02_moe_expert_002/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:824f0466bcac1c2d7327ee94266dce2837cd4b76232067a823f5be49b0e0620b +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_003.pt b/model/layer_02_moe_expert_002/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..89713a898348a9cc50652fda089d56fd17923e8e --- /dev/null +++ b/model/layer_02_moe_expert_002/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256ea2e783c3902a449f0e037baf0e2e2e16389915a420d25afb7aba65fe6a8d +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_004.pt b/model/layer_02_moe_expert_002/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..f40707da948675ed6285ba4ce5501f267cd04d62 --- /dev/null +++ b/model/layer_02_moe_expert_002/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed18eb192d8ec6930565ca7f222d50bb38f7556b4c9f117499e51c52b7820ab1 +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_005.pt b/model/layer_02_moe_expert_002/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..084cc08396dc9fe8f6a5984b7bcf179d70b4f810 --- /dev/null +++ b/model/layer_02_moe_expert_002/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30b1876221e99965d8e0305b80f0854f0ecf986134ad91c9a9c1ac8ffd0a004 +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_006.pt b/model/layer_02_moe_expert_002/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe08ea38894be2676f9ccfbcad9b8dd6df10c4a4 --- /dev/null +++ b/model/layer_02_moe_expert_002/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca44308105fa78c9b958a70c2ca90a543d0875017e4283fc021d075b75b8dd9f +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_007.pt b/model/layer_02_moe_expert_002/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..c77a291ea98050bfb7647cd5607a5f6354e0063d --- /dev/null +++ b/model/layer_02_moe_expert_002/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4db9ef6d1d0ea9ab94901107c489b1d9c69936a179481d6adfae6b309cd705 +size 2104881 diff --git a/model/layer_02_moe_expert_002/model_008.pt b/model/layer_02_moe_expert_002/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ebf6928a7118f228a562d6c894a930f5cf13a37 --- /dev/null +++ b/model/layer_02_moe_expert_002/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1f40dcdce416b3264d37c88741566dde67ea432bdac3fa976c1b269a51becd +size 2104881 diff --git a/model/layer_02_moe_expert_002/router.pt b/model/layer_02_moe_expert_002/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..642c8a139b7f2b82865c1be0a9278fc43ddea1b6 --- /dev/null +++ b/model/layer_02_moe_expert_002/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff003e0c59a75d923d85e0ab6b46bac6c22284bba69d40fd2a3093d7422c86a +size 9762 diff --git a/model/layer_02_moe_expert_003/model_001.pt b/model/layer_02_moe_expert_003/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..53c69565881f7bf74b68d5308dd97699aaa7051a --- /dev/null +++ b/model/layer_02_moe_expert_003/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230d89e5a22f7315253193b30ad75e4786835029aa8f70eb87618b4fc6d608f3 +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_002.pt b/model/layer_02_moe_expert_003/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e4b42f85d766066e84e37ba7b8fa39fddf0fae0 --- /dev/null +++ b/model/layer_02_moe_expert_003/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:424c2f1f4fe4bf2940f932aa2ffc38fac73da88011ca9e1bd1b495cfdcd91bff +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_003.pt b/model/layer_02_moe_expert_003/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e62b74e0f9e66cc9b10404ccb0a8ebb3d92b94e --- /dev/null +++ b/model/layer_02_moe_expert_003/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abd5b4e097bef8033c1d682314208eb8eadfc860e6762c1aeb5183574359ce8 +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_004.pt b/model/layer_02_moe_expert_003/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..e324ad52f6abe19c363b9a660b44c2eb12f5ad0b --- /dev/null +++ b/model/layer_02_moe_expert_003/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbdb70723a02f9a0bfe13973db825a52e976c37533a234c0fc94d63e27186ece +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_005.pt b/model/layer_02_moe_expert_003/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f9ceb6df32e23fedef914e7e218a23862627fcc --- /dev/null +++ b/model/layer_02_moe_expert_003/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f811e1a4439739bf89d7726fb2e44c4c6f1198b691708db8d0bbd82c8e4cafa +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_006.pt b/model/layer_02_moe_expert_003/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e8a074c2a7a2321f39b261b4af1866777cbb943 --- /dev/null +++ b/model/layer_02_moe_expert_003/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4ef112d47c3d39680dd00a01ee8ce73cde79ea130aba8536f5084b1477f5d0 +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_007.pt b/model/layer_02_moe_expert_003/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..af1ddc3f60264b8b4d9ce8b3d0b7a7705b05fda9 --- /dev/null +++ b/model/layer_02_moe_expert_003/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45250ab523a97e43992d9145fa25a2e4cb413e43e03133cdf5fb33aab6beb5c6 +size 2104881 diff --git a/model/layer_02_moe_expert_003/model_008.pt b/model/layer_02_moe_expert_003/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..86a790dc3ef895184aadfc15688e8227973d919d --- /dev/null +++ b/model/layer_02_moe_expert_003/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ed08d5abf3a92fa8edc81a19e36972eae8963ed027090d52ff4e9d657482f5 +size 2104881 diff --git a/model/layer_02_moe_expert_003/router.pt b/model/layer_02_moe_expert_003/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7b2e4c73ddc45a62ea9d20598937d586fdbf862 --- /dev/null +++ b/model/layer_02_moe_expert_003/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5033622632ddd9537a93d2135e7556d364aa5dc149e5071222f32e586cfccd +size 9762 diff --git a/model/layer_02_moe_expert_004/model_001.pt b/model/layer_02_moe_expert_004/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc3cf2af595263c0b6e367a494e1779d0640eca1 --- /dev/null +++ b/model/layer_02_moe_expert_004/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd2232b88e2aff90272a0b9855ce232e9b6807273f6f37645632a6ac28d68931 +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_002.pt b/model/layer_02_moe_expert_004/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d551edb313e5f818e4ba0be81e031e53bb17b84 --- /dev/null +++ b/model/layer_02_moe_expert_004/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7986380a221d650f04164b0dde30ff49dd2b7ec59e48ecc4e0993fe883b56595 +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_003.pt b/model/layer_02_moe_expert_004/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e38dd199a0cbceb0a85f0f1a90996418320bb8b --- /dev/null +++ b/model/layer_02_moe_expert_004/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b222b0b70084681b2b7071c084f795f12649f2fa5eb9649a0a98506dc01b9e1 +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_004.pt b/model/layer_02_moe_expert_004/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..91e307c85910c4d02690f49f56ba3eb6fdf091c3 --- /dev/null +++ b/model/layer_02_moe_expert_004/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1dcfdc221dc655fe8dc9e0c55320abcdfc835bdcb672b0e737ac67446acbd2 +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_005.pt b/model/layer_02_moe_expert_004/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..553a7263fddc54d909a291fbb8f576ef20f346ac --- /dev/null +++ b/model/layer_02_moe_expert_004/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f27614e010fdd9ad60f23387646e894fcfd6b9590d70d0fb4d277c024fe9e8 +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_006.pt b/model/layer_02_moe_expert_004/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..fab4e3eb0d6858eb6b041d99389c95084b21b7ec --- /dev/null +++ b/model/layer_02_moe_expert_004/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30bf068c59afab85a44c217e5d7df4a39ef3a278cf97fb761a6834a92feca559 +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_007.pt b/model/layer_02_moe_expert_004/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..191e36ec8fd51caf6d563b4ae033ec1de3000e7e --- /dev/null +++ b/model/layer_02_moe_expert_004/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cda29c6ba64ec6d8e0d9c09c4beb009cc42d06ee705b42b9f16814470c4e25d +size 2104881 diff --git a/model/layer_02_moe_expert_004/model_008.pt b/model/layer_02_moe_expert_004/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..fff81a6409b4fffcf039fb7046bc52695482506e --- /dev/null +++ b/model/layer_02_moe_expert_004/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432198ae5f8c40b8debc5004d85af137f00db6f7ea2db290147294d5803577d4 +size 2104881 diff --git a/model/layer_02_moe_expert_004/router.pt b/model/layer_02_moe_expert_004/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..70e369cd8012b896f53ec6ddc4b4c435c0136896 --- /dev/null +++ b/model/layer_02_moe_expert_004/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837c41c7078a4c0e45442c2b859c9a5ca11cdebf8d50831701565ae3f6141ab4 +size 9762 diff --git a/model/layer_02_moe_expert_005/model_001.pt b/model/layer_02_moe_expert_005/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2615470c98ea770def400b9d60371cc69bf1aa9 --- /dev/null +++ b/model/layer_02_moe_expert_005/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7eda6d21907eb3f7e8dc528f7f43372fb0e437a2a505be8cfcbec261ec7a2ca +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_002.pt b/model/layer_02_moe_expert_005/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa5ea9651cbae7e3a771e5d5b15a051856f9600b --- /dev/null +++ b/model/layer_02_moe_expert_005/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9986407f5a0bb62946a76bb6787464c1b8f46df44c90b33e127353a0e7626b +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_003.pt b/model/layer_02_moe_expert_005/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..4891cd622939ab6faf910c00a7122034cdee2f9d --- /dev/null +++ b/model/layer_02_moe_expert_005/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4713daf8a686f852d59b95796d578d893415f89902a0a9fe05fc47dfb4c2266a +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_004.pt b/model/layer_02_moe_expert_005/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d2a3d608743327da4666cae7eaf950a72d71e3d --- /dev/null +++ b/model/layer_02_moe_expert_005/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b726caa29352f92d3158025c528f5c4c7ec0cabf305384b3f78f6afc26594e +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_005.pt b/model/layer_02_moe_expert_005/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..455b18c8c7ca281c106edfade634767aba71ea48 --- /dev/null +++ b/model/layer_02_moe_expert_005/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e898b15d8581951c81a026e503b977e685d09f67392c8d0c407466c0209f59 +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_006.pt b/model/layer_02_moe_expert_005/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..45ec375f1bad763fc5cd2d7de149467bb1ad0c5c --- /dev/null +++ b/model/layer_02_moe_expert_005/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bef09dedfe067b90438b1ed988b51574137c2e2beb55bb24f19b781c6e7229c +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_007.pt b/model/layer_02_moe_expert_005/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c0c465076b776fe8860800cf88344c26741a5e9 --- /dev/null +++ b/model/layer_02_moe_expert_005/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b8d3e213f465d88bee6fd1ad38c912f56e970b07008f8367e4bef37ca5641c7 +size 2104881 diff --git a/model/layer_02_moe_expert_005/model_008.pt b/model/layer_02_moe_expert_005/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..82bf7a3f1ac06362f1ac5afb9adba1ee8a5586a3 --- /dev/null +++ b/model/layer_02_moe_expert_005/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361e77fa4eae46c8b5eab21278285985fabfedabde2dc1976de9c69b9650db43 +size 2104881 diff --git a/model/layer_02_moe_expert_005/router.pt b/model/layer_02_moe_expert_005/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..96695c18732dc51919efac2efd2fdac702c5d8b1 --- /dev/null +++ b/model/layer_02_moe_expert_005/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccc213262ce7f59ddd9e0cded8ef66b427f302e466df145d25209516b8c8eef +size 9762 diff --git a/model/layer_02_moe_expert_006/model_001.pt b/model/layer_02_moe_expert_006/model_001.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1257b98c7007061b2a3330fa3bfab1ac27ffec8 --- /dev/null +++ b/model/layer_02_moe_expert_006/model_001.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e49880e79fb1af63084376b5811caa30860fcfd37974be1b729cd1518c54d1 +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_002.pt b/model/layer_02_moe_expert_006/model_002.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c5642e622127ed13146b97be6e5b4faf741bc0b --- /dev/null +++ b/model/layer_02_moe_expert_006/model_002.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d232696bc3bc0847ae3dd96af6a88309cc93c3dda507b65c629e109cbcb205d5 +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_003.pt b/model/layer_02_moe_expert_006/model_003.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9ea618763eca09e17b55c60344b5301f63ac994 --- /dev/null +++ b/model/layer_02_moe_expert_006/model_003.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71398c4f26b620b6c26409e8cab9f9b65a254fe82d16a0d5dc77c0386fca4587 +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_004.pt b/model/layer_02_moe_expert_006/model_004.pt new file mode 100644 index 0000000000000000000000000000000000000000..3afcbcfac0787856e1c4dc108ac440322216ce24 --- /dev/null +++ b/model/layer_02_moe_expert_006/model_004.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f844e1d52fa8d3de37315cc0ee5e7a621eff40d90e19950a45f6c72ea39005c +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_005.pt b/model/layer_02_moe_expert_006/model_005.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf5b888825fdc89257ec77312f74872499115ede --- /dev/null +++ b/model/layer_02_moe_expert_006/model_005.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535da3bf12009810a72f14137dea9ae50016838e529620ddcb868ff6f0323533 +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_006.pt b/model/layer_02_moe_expert_006/model_006.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6d248b17aa23eeae6db3c49dc70c152d46a929b --- /dev/null +++ b/model/layer_02_moe_expert_006/model_006.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e7976d1c7768cf5244f331bc3a20a5016dcf39ad2a9eac4cfa081b610983ad +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_007.pt b/model/layer_02_moe_expert_006/model_007.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fa64ba3d79a1f80af7cb8135d4e11c3b224c10a --- /dev/null +++ b/model/layer_02_moe_expert_006/model_007.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffdcb35891df712a1dfd75063a277efd53bbce1a251bca69257f4be7b05c611 +size 2104881 diff --git a/model/layer_02_moe_expert_006/model_008.pt b/model/layer_02_moe_expert_006/model_008.pt new file mode 100644 index 0000000000000000000000000000000000000000..357d7894e53bbfe914b0438f5bdda5cc065d1ca1 --- /dev/null +++ b/model/layer_02_moe_expert_006/model_008.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a40f243aa6d9fb13d27a7910030249212b8a0afa6a5af8bf2bc1cefe28c64e +size 2104881 diff --git a/model/layer_02_moe_expert_006/router.pt b/model/layer_02_moe_expert_006/router.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ff50de2f6bf72261d164be7edf046fc0fa22702 --- /dev/null +++ b/model/layer_02_moe_expert_006/router.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16987b4902471a31d4a2468a5055ca0d3e43212f1fd8e12584b12eecafd86978 +size 9762 diff --git a/model/routing_log.json b/model/routing_log.json new file mode 100644 index 0000000000000000000000000000000000000000..65752e23e87dc69100471424c2a5268f55465524 --- /dev/null +++ b/model/routing_log.json @@ -0,0 +1,902 @@ +[ + { + "moe": [ + [ + 5 + ], + [ + 4 + ] + ], + "exp": [ + [ + 5 + ], + [ + 6 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 4 + ] + ], + "exp": [ + [ + 5 + ], + [ + 1 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 3 + ] + ], + "exp": [ + [ + 0 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 1 + ] + ], + "exp": [ + [ + 5 + ], + [ + 2 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 3 + ] + ], + "exp": [ + [ + 0 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 3 + ] + ], + "exp": [ + [ + 0 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 3 + ] + ], + "exp": [ + [ + 0 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 2 + ] + ], + "exp": [ + [ + 2 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 2 + ] + ], + "exp": [ + [ + 2 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 2 + ] + ], + "exp": [ + [ + 2 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 3 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 3 + ], + [ + 0 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 5 + ], + [ + 6 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 1 + ] + ], + "exp": [ + [ + 3 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 7 + ], + [ + 6 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 1 + ] + ], + "exp": [ + [ + 3 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 1 + ] + ], + "exp": [ + [ + 3 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 2 + ] + ], + "exp": [ + [ + 7 + ], + [ + 2 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 1 + ] + ], + "exp": [ + [ + 5 + ], + [ + 6 + ] + ] + }, + { + "moe": [ + [ + 3 + ], + [ + 1 + ] + ], + "exp": [ + [ + 3 + ], + [ + 4 + ] + ] + }, + { + "moe": [ + [ + 5 + ], + [ + 0 + ] + ], + "exp": [ + [ + 2 + ], + [ + 2 + ] + ] + } +] \ No newline at end of file diff --git a/model/sample.txt b/model/sample.txt new file mode 100644 index 0000000000000000000000000000000000000000..7b8a09704d3d8910bb07547fbc1c7aed3b2efcef --- /dev/null +++ b/model/sample.txt @@ -0,0 +1,7 @@ + + I w the hinat, that thisert sust te we, ist mamerat t ces + Lat athe cum. Ors amy lo anast budnd a, megheryo-n, fournop, + Bort my inowis nd wesheeinel stoug onere. + Tor at in th y murs tom dof cthe oor or meagowondshelis tt ine + Th fen. Whas mes, uke re here eas st ulong t y inonor the foturste touptn mey he masgand + As t fend chory wo be \ No newline at end of file