Upload 114 files
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- model/backbone.pt +3 -0
- model/config.json +158 -0
- model/layer_01_main_router.pt +3 -0
- model/layer_01_moe_expert_001/model_001.pt +3 -0
- model/layer_01_moe_expert_001/model_002.pt +3 -0
- model/layer_01_moe_expert_001/model_003.pt +3 -0
- model/layer_01_moe_expert_001/model_004.pt +3 -0
- model/layer_01_moe_expert_001/model_005.pt +3 -0
- model/layer_01_moe_expert_001/model_006.pt +3 -0
- model/layer_01_moe_expert_001/model_007.pt +3 -0
- model/layer_01_moe_expert_001/model_008.pt +3 -0
- model/layer_01_moe_expert_001/router.pt +3 -0
- model/layer_01_moe_expert_002/model_001.pt +3 -0
- model/layer_01_moe_expert_002/model_002.pt +3 -0
- model/layer_01_moe_expert_002/model_003.pt +3 -0
- model/layer_01_moe_expert_002/model_004.pt +3 -0
- model/layer_01_moe_expert_002/model_005.pt +3 -0
- model/layer_01_moe_expert_002/model_006.pt +3 -0
- model/layer_01_moe_expert_002/model_007.pt +3 -0
- model/layer_01_moe_expert_002/model_008.pt +3 -0
- model/layer_01_moe_expert_002/router.pt +3 -0
- model/layer_01_moe_expert_003/model_001.pt +3 -0
- model/layer_01_moe_expert_003/model_002.pt +3 -0
- model/layer_01_moe_expert_003/model_003.pt +3 -0
- model/layer_01_moe_expert_003/model_004.pt +3 -0
- model/layer_01_moe_expert_003/model_005.pt +3 -0
- model/layer_01_moe_expert_003/model_006.pt +3 -0
- model/layer_01_moe_expert_003/model_007.pt +3 -0
- model/layer_01_moe_expert_003/model_008.pt +3 -0
- model/layer_01_moe_expert_003/router.pt +3 -0
- model/layer_01_moe_expert_004/model_001.pt +3 -0
- model/layer_01_moe_expert_004/model_002.pt +3 -0
- model/layer_01_moe_expert_004/model_003.pt +3 -0
- model/layer_01_moe_expert_004/model_004.pt +3 -0
- model/layer_01_moe_expert_004/model_005.pt +3 -0
- model/layer_01_moe_expert_004/model_006.pt +3 -0
- model/layer_01_moe_expert_004/model_007.pt +3 -0
- model/layer_01_moe_expert_004/model_008.pt +3 -0
- model/layer_01_moe_expert_004/router.pt +3 -0
- model/layer_01_moe_expert_005/model_001.pt +3 -0
- model/layer_01_moe_expert_005/model_002.pt +3 -0
- model/layer_01_moe_expert_005/model_003.pt +3 -0
- model/layer_01_moe_expert_005/model_004.pt +3 -0
- model/layer_01_moe_expert_005/model_005.pt +3 -0
- model/layer_01_moe_expert_005/model_006.pt +3 -0
- model/layer_01_moe_expert_005/model_007.pt +3 -0
- model/layer_01_moe_expert_005/model_008.pt +3 -0
- model/layer_01_moe_expert_005/router.pt +3 -0
- model/layer_01_moe_expert_006/model_001.pt +3 -0
- model/layer_01_moe_expert_006/model_002.pt +3 -0
model/backbone.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c14f311274f69ff3f06722c5db2279c69a4d40038e12051d56446a77859d3232
|
| 3 |
+
size 2322241
|
model/config.json
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"block_size": 128,
|
| 4 |
+
"n_layer": 2,
|
| 5 |
+
"n_head": 4,
|
| 6 |
+
"n_embd": 256,
|
| 7 |
+
"dropout": 0.1,
|
| 8 |
+
"num_moes": 6,
|
| 9 |
+
"num_experts": 8,
|
| 10 |
+
"batch_size": 32,
|
| 11 |
+
"max_iters": 500,
|
| 12 |
+
"eval_interval": 50,
|
| 13 |
+
"eval_iters": 20,
|
| 14 |
+
"lr": 0.0003,
|
| 15 |
+
"data_file": "hamlet.txt",
|
| 16 |
+
"model_dir": "model"
|
| 17 |
+
},
|
| 18 |
+
"vocab_size": 67,
|
| 19 |
+
"step": 500,
|
| 20 |
+
"stoi": {
|
| 21 |
+
"\n": 0,
|
| 22 |
+
" ": 1,
|
| 23 |
+
"!": 2,
|
| 24 |
+
"\"": 3,
|
| 25 |
+
"&": 4,
|
| 26 |
+
"'": 5,
|
| 27 |
+
"(": 6,
|
| 28 |
+
")": 7,
|
| 29 |
+
",": 8,
|
| 30 |
+
"-": 9,
|
| 31 |
+
".": 10,
|
| 32 |
+
"1": 11,
|
| 33 |
+
":": 12,
|
| 34 |
+
";": 13,
|
| 35 |
+
"?": 14,
|
| 36 |
+
"A": 15,
|
| 37 |
+
"B": 16,
|
| 38 |
+
"C": 17,
|
| 39 |
+
"D": 18,
|
| 40 |
+
"E": 19,
|
| 41 |
+
"F": 20,
|
| 42 |
+
"G": 21,
|
| 43 |
+
"H": 22,
|
| 44 |
+
"I": 23,
|
| 45 |
+
"J": 24,
|
| 46 |
+
"K": 25,
|
| 47 |
+
"L": 26,
|
| 48 |
+
"M": 27,
|
| 49 |
+
"N": 28,
|
| 50 |
+
"O": 29,
|
| 51 |
+
"P": 30,
|
| 52 |
+
"Q": 31,
|
| 53 |
+
"R": 32,
|
| 54 |
+
"S": 33,
|
| 55 |
+
"T": 34,
|
| 56 |
+
"U": 35,
|
| 57 |
+
"V": 36,
|
| 58 |
+
"W": 37,
|
| 59 |
+
"Y": 38,
|
| 60 |
+
"[": 39,
|
| 61 |
+
"]": 40,
|
| 62 |
+
"a": 41,
|
| 63 |
+
"b": 42,
|
| 64 |
+
"c": 43,
|
| 65 |
+
"d": 44,
|
| 66 |
+
"e": 45,
|
| 67 |
+
"f": 46,
|
| 68 |
+
"g": 47,
|
| 69 |
+
"h": 48,
|
| 70 |
+
"i": 49,
|
| 71 |
+
"j": 50,
|
| 72 |
+
"k": 51,
|
| 73 |
+
"l": 52,
|
| 74 |
+
"m": 53,
|
| 75 |
+
"n": 54,
|
| 76 |
+
"o": 55,
|
| 77 |
+
"p": 56,
|
| 78 |
+
"q": 57,
|
| 79 |
+
"r": 58,
|
| 80 |
+
"s": 59,
|
| 81 |
+
"t": 60,
|
| 82 |
+
"u": 61,
|
| 83 |
+
"v": 62,
|
| 84 |
+
"w": 63,
|
| 85 |
+
"x": 64,
|
| 86 |
+
"y": 65,
|
| 87 |
+
"z": 66
|
| 88 |
+
},
|
| 89 |
+
"itos": {
|
| 90 |
+
"0": "\n",
|
| 91 |
+
"1": " ",
|
| 92 |
+
"2": "!",
|
| 93 |
+
"3": "\"",
|
| 94 |
+
"4": "&",
|
| 95 |
+
"5": "'",
|
| 96 |
+
"6": "(",
|
| 97 |
+
"7": ")",
|
| 98 |
+
"8": ",",
|
| 99 |
+
"9": "-",
|
| 100 |
+
"10": ".",
|
| 101 |
+
"11": "1",
|
| 102 |
+
"12": ":",
|
| 103 |
+
"13": ";",
|
| 104 |
+
"14": "?",
|
| 105 |
+
"15": "A",
|
| 106 |
+
"16": "B",
|
| 107 |
+
"17": "C",
|
| 108 |
+
"18": "D",
|
| 109 |
+
"19": "E",
|
| 110 |
+
"20": "F",
|
| 111 |
+
"21": "G",
|
| 112 |
+
"22": "H",
|
| 113 |
+
"23": "I",
|
| 114 |
+
"24": "J",
|
| 115 |
+
"25": "K",
|
| 116 |
+
"26": "L",
|
| 117 |
+
"27": "M",
|
| 118 |
+
"28": "N",
|
| 119 |
+
"29": "O",
|
| 120 |
+
"30": "P",
|
| 121 |
+
"31": "Q",
|
| 122 |
+
"32": "R",
|
| 123 |
+
"33": "S",
|
| 124 |
+
"34": "T",
|
| 125 |
+
"35": "U",
|
| 126 |
+
"36": "V",
|
| 127 |
+
"37": "W",
|
| 128 |
+
"38": "Y",
|
| 129 |
+
"39": "[",
|
| 130 |
+
"40": "]",
|
| 131 |
+
"41": "a",
|
| 132 |
+
"42": "b",
|
| 133 |
+
"43": "c",
|
| 134 |
+
"44": "d",
|
| 135 |
+
"45": "e",
|
| 136 |
+
"46": "f",
|
| 137 |
+
"47": "g",
|
| 138 |
+
"48": "h",
|
| 139 |
+
"49": "i",
|
| 140 |
+
"50": "j",
|
| 141 |
+
"51": "k",
|
| 142 |
+
"52": "l",
|
| 143 |
+
"53": "m",
|
| 144 |
+
"54": "n",
|
| 145 |
+
"55": "o",
|
| 146 |
+
"56": "p",
|
| 147 |
+
"57": "q",
|
| 148 |
+
"58": "r",
|
| 149 |
+
"59": "s",
|
| 150 |
+
"60": "t",
|
| 151 |
+
"61": "u",
|
| 152 |
+
"62": "v",
|
| 153 |
+
"63": "w",
|
| 154 |
+
"64": "x",
|
| 155 |
+
"65": "y",
|
| 156 |
+
"66": "z"
|
| 157 |
+
}
|
| 158 |
+
}
|
model/layer_01_main_router.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc4803c65495a8d77e08bbe1d62ac1136c314602ba2a47045b3abdd13e8a86c
|
| 3 |
+
size 7876
|
model/layer_01_moe_expert_001/model_001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:114b7753a3bf94e2db56f3d91be012e15f8bd962ebb5a223f483cc73eb679b87
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9bd91795ea832e2d96ffd398d8a7018a8e8a27aebfd6e6c8088996b1b5c4da3
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_003.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4f2b8d4f745224c99c89b1b5c96f78271051e9578c0b07c34579657da49c01f
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_004.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96d936b1c83a8229c36032bd2d6d60b92b34fc8ab96305eaa361fc23cb1113e9
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_005.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a4e35cd1b9d6cdeaa6feec76ed2f65aff45da24dc5c2480c0272a4ba19e817f
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_006.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb8aac1c7afb24e2e46077cc0ec6d3fd12863eb3cee8ca2392f4f9bbed149eb7
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_007.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfeb19445b93c0afb05e1a82150a83d6dd8feae22a7fe24125d01f45d3160920
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/model_008.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecdb7fad20a47de1e9148d68b39c737f11eca894066fd375c8adb9fd32470a4c
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_001/router.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea3916190906b36a1dc8f6eabebcbf6c3ad7975657c3a395a80ffd18dcaeac72
|
| 3 |
+
size 9762
|
model/layer_01_moe_expert_002/model_001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6665fc870417fa735b533eebf2e56c0a7fa9da5b3680dd18b6f59cd2fae3e6b8
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0161939d4709ccfb1fc84f243300d8bc79136f834f4bf53298f25752529eb8fd
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_003.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2b0358fad9b1c03f5ff52bfe19a8187d933442a18da50f9dd6587f01a5b6d17
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_004.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6127d6e715972db1da1389edae44308b286b3741af73a13316916c1cccdbaee
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_005.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70c2a712da9c4c26419d692b48a54e88aa7db8809b65a5d774cbcdd740d756db
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_006.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8baaa6b100a00e395407aadae45289d1324eee3def44c4c56f31117fe2f0a770
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_007.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77e4d9de453dcca691c5f9656558f2e26032f34e835640c657e350b36b61ba50
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/model_008.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7bebae9d8814ee53ab9729f18a68e2e05e93d6d7057e1d4546084cf264f93ee
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_002/router.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff877d6965348142d4bf0e86a64e3217459cf810fdaf860fddbcd975e8e5b86b
|
| 3 |
+
size 9762
|
model/layer_01_moe_expert_003/model_001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d27e9f596512a3e624205dbde10031b47c23bcce52e75ca893c93fb7d19bcb4d
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ce623d27c15f1a555e9718a93469d17a448cc87001439d4d22e2e5ea62b47d7
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_003.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc9232187d4a5382b64e18a51f40e210cd1818dd22c5fa14a2dc8fde12d30984
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_004.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:518a9235d19b3ef4e8a2ec8f8a5a97ff586df52bfc3748702ae86c826770db4f
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_005.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35422170b4f6ac417ce2b1df1e4548c678bdc5e4969ff3f7266ed9c97f47dc80
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_006.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b91b87c4971c6b394c8664db8a8fba0cef2e438e964bfb4283fae6c2c6e1252a
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_007.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff1ec132722af4fc7f30b5db9c744268c09e7c4bc9f2cd855a72deec00b1d00f
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/model_008.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:555d2114d7bd519465a1e4adf355de0bff3b1ed138e9873760bcc55e650f7732
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_003/router.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1af3f77b22f11f620388c7b2294ccdd80ea950ffb80fa221f8b62ba292656861
|
| 3 |
+
size 9762
|
model/layer_01_moe_expert_004/model_001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cfa44526869e13728f27d122ed32b19818f6a7af8c1881cb3bf7fc850a2566e
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5856ed69a4512d58b9c19409f428f24ac2c9b5817c49bb2fd35da3a443276729
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_003.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28eef58ff4522c7bfaae14a459bc860519b9c4aef6abe15d2d5695d7d1f954cc
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_004.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a20fe86108c4196bf76936386e4eed81ca1b25493413c05b91cde26fe759a0fd
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_005.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7137bfe0563d259f3bab97c65c5d2664325eaa6c3a21fd4af0abc69d7c237b5d
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_006.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac98a8a0924e1ed83f55ae9d3f372f3509a10de35aeccb4a5151b8a5fc37242
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_007.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc727bdb594a4d91d5ed4b93bcc5f7127b59e664fcf9df584de0fd1e74b96898
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/model_008.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0e893a286f95d30c556af59ed4bffaf77f8cab15bb7be9d5af5f7940adc613b
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_004/router.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:668147605eae36465c25d5863fe87fe0ef05e17c8ebd0c0b9bd971eca18ff650
|
| 3 |
+
size 9762
|
model/layer_01_moe_expert_005/model_001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a1d0348ce078ed41ad04ad00a5725256e7236ac2f4d3c67cc363298aa773b4e
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0920db81b9187797f8b9f7c6d36ce826d09caca2bb3aed91c6712d2755f542e
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_003.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7331974b3d1f5374064b0c7b2ed77b3e1cc8995c18aaee7106c2164ecef9b71b
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_004.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a12bc8747c96d40bc2c492de3ccc543e3f97a6c5899cdcc5b8bd0409b37ef357
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_005.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a2ec04f332479ceefc6780c365bd799da239b451a399e54d9fe23757a89e081
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_006.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca2f03e2bfeb6a1eab173aad761da2b48ca037def1ba1649d6f41c93ce101f31
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_007.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bb3850cc3e37f20c245c982ce24fb2c2d477c63b01900fb980c2af61cc60cdb
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/model_008.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19679e22d959ad56b73545822374214accada6fc8efa84db13c9505123b110f5
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_005/router.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f48182bbd38ea1d96ac1f919ac10db7fde53151756beae3eb8c88f6998ff3c1e
|
| 3 |
+
size 9762
|
model/layer_01_moe_expert_006/model_001.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e90c20e2018258584dde8679f973a58051285cf326723e5e3d6188ccb920a32
|
| 3 |
+
size 2104881
|
model/layer_01_moe_expert_006/model_002.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4279cdec0065b03c6b6c4325ae68b76aac95156625e1bc74349e7e07dd028cab
|
| 3 |
+
size 2104881
|