Lin-K76 commited on
Commit
2d04e49
1 Parent(s): 904d9b9

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -21,63 +21,63 @@
21
  "quantization_config": {
22
  "activation_scheme": "static",
23
  "ignored_layers": [
24
- "model.layers.55.block_sparse_moe.gate",
25
  "model.layers.0.block_sparse_moe.gate",
26
- "model.layers.36.block_sparse_moe.gate",
27
  "model.layers.2.block_sparse_moe.gate",
28
- "model.layers.8.block_sparse_moe.gate",
29
- "model.layers.40.block_sparse_moe.gate",
30
  "model.layers.11.block_sparse_moe.gate",
31
- "model.layers.15.block_sparse_moe.gate",
32
- "model.layers.23.block_sparse_moe.gate",
33
- "model.layers.10.block_sparse_moe.gate",
 
 
 
 
 
34
  "model.layers.7.block_sparse_moe.gate",
 
 
35
  "model.layers.38.block_sparse_moe.gate",
36
- "model.layers.43.block_sparse_moe.gate",
37
- "model.layers.53.block_sparse_moe.gate",
38
- "model.layers.1.block_sparse_moe.gate",
39
- "model.layers.37.block_sparse_moe.gate",
40
- "model.layers.54.block_sparse_moe.gate",
41
  "model.layers.24.block_sparse_moe.gate",
42
- "model.layers.28.block_sparse_moe.gate",
43
- "model.layers.41.block_sparse_moe.gate",
44
- "model.layers.17.block_sparse_moe.gate",
45
  "model.layers.45.block_sparse_moe.gate",
46
- "model.layers.6.block_sparse_moe.gate",
47
- "model.layers.20.block_sparse_moe.gate",
48
- "model.layers.25.block_sparse_moe.gate",
49
- "model.layers.34.block_sparse_moe.gate",
50
- "model.layers.12.block_sparse_moe.gate",
51
- "model.layers.26.block_sparse_moe.gate",
52
- "model.layers.50.block_sparse_moe.gate",
53
  "lm_head",
 
 
 
 
 
54
  "model.layers.19.block_sparse_moe.gate",
55
- "model.layers.48.block_sparse_moe.gate",
56
- "model.layers.33.block_sparse_moe.gate",
57
  "model.layers.4.block_sparse_moe.gate",
58
- "model.layers.29.block_sparse_moe.gate",
59
- "model.layers.44.block_sparse_moe.gate",
60
- "model.layers.16.block_sparse_moe.gate",
61
  "model.layers.42.block_sparse_moe.gate",
62
- "model.layers.30.block_sparse_moe.gate",
 
63
  "model.layers.51.block_sparse_moe.gate",
64
- "model.layers.21.block_sparse_moe.gate",
65
- "model.layers.18.block_sparse_moe.gate",
66
- "model.layers.32.block_sparse_moe.gate",
67
- "model.layers.35.block_sparse_moe.gate",
68
- "model.layers.49.block_sparse_moe.gate",
69
  "model.layers.14.block_sparse_moe.gate",
70
  "model.layers.31.block_sparse_moe.gate",
71
- "model.layers.47.block_sparse_moe.gate",
72
- "model.layers.22.block_sparse_moe.gate",
73
- "model.layers.3.block_sparse_moe.gate",
74
- "model.layers.46.block_sparse_moe.gate",
75
- "model.layers.9.block_sparse_moe.gate",
76
- "model.layers.13.block_sparse_moe.gate",
77
  "model.layers.39.block_sparse_moe.gate",
78
- "model.layers.52.block_sparse_moe.gate",
79
  "model.layers.5.block_sparse_moe.gate",
80
- "model.layers.27.block_sparse_moe.gate"
 
 
 
 
 
 
 
 
 
 
 
 
81
  ],
82
  "quant_method": "fp8"
83
  },
@@ -88,7 +88,7 @@
88
  "sliding_window": null,
89
  "tie_word_embeddings": false,
90
  "torch_dtype": "bfloat16",
91
- "transformers_version": "4.41.2",
92
  "use_cache": true,
93
  "vocab_size": 32768
94
  }
 
21
  "quantization_config": {
22
  "activation_scheme": "static",
23
  "ignored_layers": [
 
24
  "model.layers.0.block_sparse_moe.gate",
 
25
  "model.layers.2.block_sparse_moe.gate",
 
 
26
  "model.layers.11.block_sparse_moe.gate",
27
+ "model.layers.16.block_sparse_moe.gate",
28
+ "model.layers.13.block_sparse_moe.gate",
29
+ "model.layers.28.block_sparse_moe.gate",
30
+ "model.layers.46.block_sparse_moe.gate",
31
+ "model.layers.50.block_sparse_moe.gate",
32
+ "model.layers.9.block_sparse_moe.gate",
33
+ "model.layers.17.block_sparse_moe.gate",
34
+ "model.layers.27.block_sparse_moe.gate",
35
  "model.layers.7.block_sparse_moe.gate",
36
+ "model.layers.23.block_sparse_moe.gate",
37
+ "model.layers.25.block_sparse_moe.gate",
38
  "model.layers.38.block_sparse_moe.gate",
39
+ "model.layers.55.block_sparse_moe.gate",
40
+ "model.layers.47.block_sparse_moe.gate",
41
+ "model.layers.48.block_sparse_moe.gate",
42
+ "model.layers.29.block_sparse_moe.gate",
 
43
  "model.layers.24.block_sparse_moe.gate",
 
 
 
44
  "model.layers.45.block_sparse_moe.gate",
 
 
 
 
 
 
 
45
  "lm_head",
46
+ "model.layers.40.block_sparse_moe.gate",
47
+ "model.layers.1.block_sparse_moe.gate",
48
+ "model.layers.15.block_sparse_moe.gate",
49
+ "model.layers.37.block_sparse_moe.gate",
50
+ "model.layers.22.block_sparse_moe.gate",
51
  "model.layers.19.block_sparse_moe.gate",
52
+ "model.layers.20.block_sparse_moe.gate",
53
+ "model.layers.32.block_sparse_moe.gate",
54
  "model.layers.4.block_sparse_moe.gate",
55
+ "model.layers.34.block_sparse_moe.gate",
 
 
56
  "model.layers.42.block_sparse_moe.gate",
57
+ "model.layers.43.block_sparse_moe.gate",
58
+ "model.layers.8.block_sparse_moe.gate",
59
  "model.layers.51.block_sparse_moe.gate",
60
+ "model.layers.41.block_sparse_moe.gate",
61
+ "model.layers.10.block_sparse_moe.gate",
62
+ "model.layers.6.block_sparse_moe.gate",
63
+ "model.layers.33.block_sparse_moe.gate",
 
64
  "model.layers.14.block_sparse_moe.gate",
65
  "model.layers.31.block_sparse_moe.gate",
 
 
 
 
 
 
66
  "model.layers.39.block_sparse_moe.gate",
 
67
  "model.layers.5.block_sparse_moe.gate",
68
+ "model.layers.49.block_sparse_moe.gate",
69
+ "model.layers.53.block_sparse_moe.gate",
70
+ "model.layers.26.block_sparse_moe.gate",
71
+ "model.layers.36.block_sparse_moe.gate",
72
+ "model.layers.35.block_sparse_moe.gate",
73
+ "model.layers.3.block_sparse_moe.gate",
74
+ "model.layers.52.block_sparse_moe.gate",
75
+ "model.layers.18.block_sparse_moe.gate",
76
+ "model.layers.54.block_sparse_moe.gate",
77
+ "model.layers.30.block_sparse_moe.gate",
78
+ "model.layers.44.block_sparse_moe.gate",
79
+ "model.layers.12.block_sparse_moe.gate",
80
+ "model.layers.21.block_sparse_moe.gate"
81
  ],
82
  "quant_method": "fp8"
83
  },
 
88
  "sliding_window": null,
89
  "tie_word_embeddings": false,
90
  "torch_dtype": "bfloat16",
91
+ "transformers_version": "4.44.0",
92
  "use_cache": true,
93
  "vocab_size": 32768
94
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.41.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.44.0"
6
  }
model-00001-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b9fd1bf1820131291ecc53097e9f01963df9b636dfeacb5cd0d491d892dd0e8
3
  size 4907575696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee319f48d49b75e891e0a1d9605c213a3ebb4957372a998688ea65af1d1b6ed9
3
  size 4907575696
model-00002-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80c86c023c75d4ea23d9e89ef602dbec3a6c8db837e3fd4656d9c201c615cef3
3
  size 4907601808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e0c0d3cd5dd457af8b3b35f378c1b21029200b8e137c0aca159020c2d80111
3
  size 4907601808
model-00003-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5055964602f29228e5e3715d514b7d490880c84deaf22b855e5714e3da5b2a1
3
  size 4907601808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d007bfecee90bb5fae1bdf4752fad96d92e543085c6c154b62da070b9f1404
3
  size 4907601808
model-00004-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:497ddf951a49f27e6a03efbbe0df106d1b7ce351b4008df5caae2877953f05f8
3
  size 4907601808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65553a5dbf11a1cad09c87b1cf78d1f9b0481f6e57bcf92eeaf799a83a36228
3
  size 4907601808
model-00005-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd29ac1a2126c2b70bfa5c66344afb1b74a03003dd64390438eb4e89bd66c5f1
3
  size 4907601808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27f76351f6ddde6d9d04bfe9037e3f9896a6d89880e4441bab8312ef08b5fd1
3
  size 4907601808
model-00006-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76df8b4518e0b9a681f7873eb2d9e447dc76f4b50c0da8ab84616e6bcea0a7d2
3
  size 4907601952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72e6e3987921ff8b471e8614717dc0021a18e4e2444d822d153a969e6d8a05a
3
  size 4907601952
model-00007-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32e7e0565cdc76c70e337c8434d897e858090749c23f8a8eb1463dce988cbb6d
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead8d399d5b66c21ef162d6a5d62f9802797bf0342ed233160d13965241537cd
3
  size 4907601976
model-00008-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a7fdebfc190def06160df1a29b3caa28874d8de1ee0470a5c16faeea69ca92e
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c168c78a24184a2671eca22721ee00e8aca344525b3b37b84aec69b681074c
3
  size 4907601976
model-00009-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a1cd5fbb538b130b3a23aa251ef1cecff8d6087d0d881506dddc9327640988a
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bd863fc6b71020cdc440b34849615bd4dd5a0eba24696391503c83c2f6234a
3
  size 4907601976
model-00010-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3411f179c7098c112fbc07bce52cbd08e5de0cf68e718fc3486bc7ac0c92511a
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9acd87442f96a89a755a2f01a3fec95f4595904b8312b4c9693a59f09842c3
3
  size 4907601976
model-00011-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48e99303ff5e2f842b19c3bf18da8fe846c05ad4ef26eb63d110ff870d6cfe1d
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cad9c04285332f0f6a4089f836bda195c125e59f0544305a75a56a4dd4a3a72
3
  size 4907601976
model-00012-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e2d921e191feb8441e762a492094bbcc94dcfcac26ca322f8c443da02278a5
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:314aba78483bee592480defc6175b1e0bf9437cc8eb1e6ba462852a3ec2bffa9
3
  size 4907601976
model-00013-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5512fd75fd75118e95fafee9aff4d0ab1ba651050d542a6d62d9efc238290618
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062da3f57fe9aabef96c66e32ad7642ce6ad7720064eb60a16ac1f67edd98a4b
3
  size 4907601976
model-00014-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:484bc510c824bacd410f85f874a49951bed8e01b4878ad0f47f3113134db0684
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41c644a55b1d336254614aebf82428881c9af9fc7119038d6530e964f6c07ae
3
  size 4907601976
model-00015-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88c5f317d94a603029d07879f2ac8b930b3041b787fb5fbd73ebe5556df0bbc0
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf57947ce88d0985b2c3fd428474af118bbb590fe4f6e5ebb740a4496df4b59
3
  size 4907601976
model-00016-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7f1cadb9eff927459aeaef7dc9e9327ea34e634cdd8863dd11c5448f8b0f3bf
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102ee567bec845b9022f0f4bf2d89a85457565d05ad6c8f52bceadf4e05e1fc9
3
  size 4907601976
model-00017-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf015a92807ff1fdc144890ec704d0bfc3849eb92063b68fa3d121cda57477dc
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965e561108fb460634c97c228858b10acd274d77685cc3402a4fc4e5b844eefc
3
  size 4907601976
model-00018-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3ce405075879cfb31269de08648cbe768c511287a58942c8dd4d58790dcbea4
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628bec3f5755495aeedefe5ed1c0dddc5d7c3ec82a3fc72c16810f54ca455615
3
  size 4907601976
model-00019-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ba0d4a1c5285221b3546c1408c0322fa767e7a46ff81a4d501256245de9c521
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931a0b559720ace58166354394cef5e6ebb53eebdfcfa5d68d07a804f2929d95
3
  size 4907601976
model-00020-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d2fd2dc4feedfa6d884a1b436250aa901ded80fba6cab78bce38aa1c428ad62
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541e5daf7a2075a7ad1436bca65ee541081e66d27b4f47e791820b21f1b4e399
3
  size 4907601976
model-00021-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f38d5833f9d845481d56bfe336d554599ebdf1dcdbee71ad85ef94cb97b9b62d
3
  size 4970418160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7397455ced2446c5fa05f0f2f3d2e832ecfe3494a83e0b969de7f9e7e717a20
3
  size 4970418160
model-00022-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2e2614b99ebaf1e7a6b0613fd02098421f5f3a57754f4a2b475633de3415c69
3
  size 4995682080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0d99e695af6c085ea7ad3e383e73017e2642417ac6045a3061d5393d684023
3
  size 4995682080
model-00023-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd5c92ac521e109306b960e43fcb6ff74852324518e7eab7985ff0ac49603cd7
3
  size 4970516584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e9f15826256ddef6a22496af0314e4c9089e9cb8efc62159c9dc751dd37c90
3
  size 4970516584
model-00024-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b79d06fcd1dce85215273f956fa8aad2460ad3a67df6d317fd8eddda1b66609
3
  size 4907577184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85f066b5947d7de1d8d7f2b70eefef6845fa92b2d1e434cd1cfd95668877dd9
3
  size 4907577184
model-00025-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5184119557e2640e08dd892562b8ffc5a47b4c73390c0f1bef5057a9c6ab43d7
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51c495c7e7cdf21b5bd231232cec4e71ef2e31ec43a5713dad65cc2c12c6436
3
  size 4907601976
model-00026-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:699e2e62245c205ce1a5676a9f4a398dca3928e3a2a6c1cdb849e77ff35e061a
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47b290aa38ff2961dc7657e73abcc3cd2037dc8f6f04166e26757f231f17807
3
  size 4907601976
model-00027-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16b2d35138e1157153d3bfea0790b3260baae3ce3346e5adecff248f314b7088
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e06dc497df69d95060086363803634cf6ddd68bf5af03092633f74cfd213bb
3
  size 4907601976
model-00028-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed08a4b8c2d63bb036758dfd4b2c6d894461ecdb7b836cbf5d009ae0c9f4a89e
3
  size 4907601976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c533f27551b7e7a6e275e11f1b6cdb6b07e718da07a4cb581e356ad6cc62a3d
3
  size 4907601976
model-00029-of-00029.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45cfc14555c6e8bbe7656435203c0da1f936890cdd401402d80a12f86036e836
3
  size 3410141608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c65e2ebe21f4a831ee4d78c2dc19c7b07405b47cc574bc01a36c6bf374dc402
3
  size 3410141608
special_tokens_map.json CHANGED
@@ -2,21 +2,21 @@
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
- "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
19
- "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  }
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
19
+ "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff