Update models
Browse files- .gitattributes +15 -0
- Phi-3.5-MoE-instruct-Q2_K.gguf +3 -0
- Phi-3.5-MoE-instruct-Q3_K_L.gguf +3 -0
- Phi-3.5-MoE-instruct-Q3_K_M.gguf +3 -0
- Phi-3.5-MoE-instruct-Q3_K_S.gguf +3 -0
- Phi-3.5-MoE-instruct-Q4_0.gguf +3 -0
- Phi-3.5-MoE-instruct-Q4_K_M.gguf +3 -0
- Phi-3.5-MoE-instruct-Q4_K_S.gguf +3 -0
- Phi-3.5-MoE-instruct-Q5_0.gguf +3 -0
- Phi-3.5-MoE-instruct-Q5_K_M.gguf +3 -0
- Phi-3.5-MoE-instruct-Q5_K_S.gguf +3 -0
- Phi-3.5-MoE-instruct-Q6_K.gguf +3 -0
- Phi-3.5-MoE-instruct-Q8_0.gguf +3 -0
- Phi-3.5-MoE-instruct-f16-00001-of-00003.gguf +3 -0
- Phi-3.5-MoE-instruct-f16-00002-of-00003.gguf +3 -0
- Phi-3.5-MoE-instruct-f16-00003-of-00003.gguf +3 -0
- config.json +178 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
Phi-3.5-MoE-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Phi-3.5-MoE-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Phi-3.5-MoE-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Phi-3.5-MoE-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Phi-3.5-MoE-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Phi-3.5-MoE-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
Phi-3.5-MoE-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
Phi-3.5-MoE-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
Phi-3.5-MoE-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
Phi-3.5-MoE-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
Phi-3.5-MoE-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
Phi-3.5-MoE-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
Phi-3.5-MoE-instruct-f16-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
Phi-3.5-MoE-instruct-f16-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
Phi-3.5-MoE-instruct-f16-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
Phi-3.5-MoE-instruct-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a040855e6fc6b851b8f8f8bc90fded7e65a0aa23e29e34009fbb28bd5828b34
|
| 3 |
+
size 15265136192
|
Phi-3.5-MoE-instruct-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c46d31812f3d1ea0c1187aff2c0f7c76e0ac8c455d7d145738741f615ef252
|
| 3 |
+
size 21688419904
|
Phi-3.5-MoE-instruct-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26f6241d683fac3a8716dbc77b1fdaac6bafdfce9be8bacb7a25c3925a09ed9d
|
| 3 |
+
size 20032718400
|
Phi-3.5-MoE-instruct-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9734b58d5dc8622cf38e7e013bb4d9aeaec27c41e39e4e4232bc27ab7bc093d2
|
| 3 |
+
size 18055104064
|
Phi-3.5-MoE-instruct-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5369b4df151ec39500ecad8a967d8565c8c837d690ec5dafef1b10a253e70038
|
| 3 |
+
size 23598542400
|
Phi-3.5-MoE-instruct-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8754cbff74872f0cc96dc77ddec093ee9e565f3f62ce61e0877201bc2661b55e
|
| 3 |
+
size 25345994304
|
Phi-3.5-MoE-instruct-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55579ac0f665be108c4aa1b852fe8cdc7deaaa04862b5c7114258ce4ed39f58d
|
| 3 |
+
size 23810354752
|
Phi-3.5-MoE-instruct-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f508922902a38743a7ea5095221e49afe8140e4c363cf02beb06768aa547b9e
|
| 3 |
+
size 28815896128
|
Phi-3.5-MoE-instruct-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08a765378ad6dd01cd1b3bb79c937650bb2658ad1fa66123b695a1dcc9fb7631
|
| 3 |
+
size 29716098624
|
Phi-3.5-MoE-instruct-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe5c7bc0b2d20d35c7c470677ab1360880647c9b8a5e1e1f0b9f18dc1536e05f
|
| 3 |
+
size 28815896128
|
Phi-3.5-MoE-instruct-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5911f51f7d4d028c0d9b90be2cdfcc623f635e6a50b5da4d155177618040444
|
| 3 |
+
size 34359334464
|
Phi-3.5-MoE-instruct-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78b129ebf4b5c11635ad373b1ab5ce42ab180d9aba888dc2f8e2caec6094712c
|
| 3 |
+
size 44499764800
|
Phi-3.5-MoE-instruct-f16-00001-of-00003.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:462a5f9d0d7a704e754b43a3d013663d77e22881c40f34303b576b6ec90f73e0
|
| 3 |
+
size 29795665152
|
Phi-3.5-MoE-instruct-f16-00002-of-00003.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a85032a4f8c3f1d904784d9bcde112ff658f27bf5a7f42364a72a281a18d8fa2
|
| 3 |
+
size 29448079808
|
Phi-3.5-MoE-instruct-f16-00003-of-00003.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a48bd2bad7e609ff43e01db750f03e53f145a37c754a9d216baca8da35191f7
|
| 3 |
+
size 24509298912
|
config.json
ADDED
|
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Phi-3.5-MoE-instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiMoEForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phimoe.PhiMoEConfig",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phimoe.PhiMoEForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"eos_token_id": 32000,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_dropout": 0.0,
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"input_jitter_noise": 0.01,
|
| 19 |
+
"intermediate_size": 6400,
|
| 20 |
+
"lm_head_bias": true,
|
| 21 |
+
"max_position_embeddings": 131072,
|
| 22 |
+
"model_type": "phimoe",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_experts_per_tok": 2,
|
| 25 |
+
"num_hidden_layers": 32,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"num_local_experts": 16,
|
| 28 |
+
"original_max_position_embeddings": 4096,
|
| 29 |
+
"output_router_logits": false,
|
| 30 |
+
"rms_norm_eps": 1e-05,
|
| 31 |
+
"rope_scaling": {
|
| 32 |
+
"long_factor": [
|
| 33 |
+
1.0199999809265137,
|
| 34 |
+
1.0299999713897705,
|
| 35 |
+
1.0399999618530273,
|
| 36 |
+
1.0499999523162842,
|
| 37 |
+
1.0499999523162842,
|
| 38 |
+
1.0499999523162842,
|
| 39 |
+
1.059999942779541,
|
| 40 |
+
1.059999942779541,
|
| 41 |
+
1.059999942779541,
|
| 42 |
+
1.059999942779541,
|
| 43 |
+
1.059999942779541,
|
| 44 |
+
1.059999942779541,
|
| 45 |
+
1.0999999046325684,
|
| 46 |
+
1.1799999475479126,
|
| 47 |
+
1.1799999475479126,
|
| 48 |
+
1.3700000047683716,
|
| 49 |
+
1.4899998903274536,
|
| 50 |
+
2.109999895095825,
|
| 51 |
+
2.8899998664855957,
|
| 52 |
+
3.9499998092651367,
|
| 53 |
+
4.299999713897705,
|
| 54 |
+
6.429999828338623,
|
| 55 |
+
8.09000015258789,
|
| 56 |
+
10.690000534057617,
|
| 57 |
+
12.050000190734863,
|
| 58 |
+
18.229999542236328,
|
| 59 |
+
18.84000015258789,
|
| 60 |
+
19.899999618530273,
|
| 61 |
+
21.420000076293945,
|
| 62 |
+
26.200000762939453,
|
| 63 |
+
34.28000259399414,
|
| 64 |
+
34.590003967285156,
|
| 65 |
+
38.730003356933594,
|
| 66 |
+
40.22000503540039,
|
| 67 |
+
42.54000473022461,
|
| 68 |
+
44.000003814697266,
|
| 69 |
+
47.590003967285156,
|
| 70 |
+
54.750003814697266,
|
| 71 |
+
56.19000244140625,
|
| 72 |
+
57.44000244140625,
|
| 73 |
+
57.4900016784668,
|
| 74 |
+
61.20000076293945,
|
| 75 |
+
61.540000915527344,
|
| 76 |
+
61.75,
|
| 77 |
+
61.779998779296875,
|
| 78 |
+
62.06999969482422,
|
| 79 |
+
63.11000061035156,
|
| 80 |
+
63.43000030517578,
|
| 81 |
+
63.560001373291016,
|
| 82 |
+
63.71000289916992,
|
| 83 |
+
63.92000198364258,
|
| 84 |
+
63.94000244140625,
|
| 85 |
+
63.94000244140625,
|
| 86 |
+
63.96000289916992,
|
| 87 |
+
63.980003356933594,
|
| 88 |
+
64.0300064086914,
|
| 89 |
+
64.0300064086914,
|
| 90 |
+
64.0300064086914,
|
| 91 |
+
64.04000854492188,
|
| 92 |
+
64.10000610351562,
|
| 93 |
+
64.19000244140625,
|
| 94 |
+
64.20999908447266,
|
| 95 |
+
64.75,
|
| 96 |
+
64.95999908447266
|
| 97 |
+
],
|
| 98 |
+
"long_mscale": 1.243163121016122,
|
| 99 |
+
"original_max_position_embeddings": 4096,
|
| 100 |
+
"short_factor": [
|
| 101 |
+
1.0,
|
| 102 |
+
1.0399999618530273,
|
| 103 |
+
1.0399999618530273,
|
| 104 |
+
1.0399999618530273,
|
| 105 |
+
1.0499999523162842,
|
| 106 |
+
1.0499999523162842,
|
| 107 |
+
1.0499999523162842,
|
| 108 |
+
1.0499999523162842,
|
| 109 |
+
1.0499999523162842,
|
| 110 |
+
1.0499999523162842,
|
| 111 |
+
1.0499999523162842,
|
| 112 |
+
1.0499999523162842,
|
| 113 |
+
1.0499999523162842,
|
| 114 |
+
1.0499999523162842,
|
| 115 |
+
1.059999942779541,
|
| 116 |
+
1.059999942779541,
|
| 117 |
+
1.0699999332427979,
|
| 118 |
+
1.0699999332427979,
|
| 119 |
+
1.0699999332427979,
|
| 120 |
+
1.0699999332427979,
|
| 121 |
+
1.1399999856948853,
|
| 122 |
+
1.159999966621399,
|
| 123 |
+
1.159999966621399,
|
| 124 |
+
1.159999966621399,
|
| 125 |
+
1.159999966621399,
|
| 126 |
+
1.1799999475479126,
|
| 127 |
+
1.1999999284744263,
|
| 128 |
+
1.3199999332427979,
|
| 129 |
+
1.3399999141693115,
|
| 130 |
+
1.3499999046325684,
|
| 131 |
+
1.3999998569488525,
|
| 132 |
+
1.4799998998641968,
|
| 133 |
+
1.4999998807907104,
|
| 134 |
+
1.589999794960022,
|
| 135 |
+
1.6499998569488525,
|
| 136 |
+
1.71999990940094,
|
| 137 |
+
1.8999998569488525,
|
| 138 |
+
1.9099998474121094,
|
| 139 |
+
1.9099998474121094,
|
| 140 |
+
1.9899998903274536,
|
| 141 |
+
1.9999998807907104,
|
| 142 |
+
1.9999998807907104,
|
| 143 |
+
2.009999990463257,
|
| 144 |
+
2.009999990463257,
|
| 145 |
+
2.009999990463257,
|
| 146 |
+
2.009999990463257,
|
| 147 |
+
2.009999990463257,
|
| 148 |
+
2.009999990463257,
|
| 149 |
+
2.009999990463257,
|
| 150 |
+
2.009999990463257,
|
| 151 |
+
2.009999990463257,
|
| 152 |
+
2.009999990463257,
|
| 153 |
+
2.009999990463257,
|
| 154 |
+
2.009999990463257,
|
| 155 |
+
2.009999990463257,
|
| 156 |
+
2.009999990463257,
|
| 157 |
+
2.009999990463257,
|
| 158 |
+
2.009999990463257,
|
| 159 |
+
2.009999990463257,
|
| 160 |
+
2.0999999046325684,
|
| 161 |
+
2.319999933242798,
|
| 162 |
+
2.419999837875366,
|
| 163 |
+
2.5899999141693115,
|
| 164 |
+
2.7899999618530273
|
| 165 |
+
],
|
| 166 |
+
"short_mscale": 1.243163121016122,
|
| 167 |
+
"type": "longrope"
|
| 168 |
+
},
|
| 169 |
+
"rope_theta": 10000.0,
|
| 170 |
+
"router_aux_loss_coef": 0.0,
|
| 171 |
+
"router_jitter_noise": 0.01,
|
| 172 |
+
"sliding_window": 131072,
|
| 173 |
+
"tie_word_embeddings": false,
|
| 174 |
+
"torch_dtype": "bfloat16",
|
| 175 |
+
"transformers_version": "4.43.3",
|
| 176 |
+
"use_cache": true,
|
| 177 |
+
"vocab_size": 32064
|
| 178 |
+
}
|