This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. config.json +3 -40
  2. generation_config.json +1 -1
  3. model-00001-of-00194.safetensors +3 -0
  4. model-00002-of-00194.safetensors +3 -0
  5. model-00003-of-00194.safetensors +3 -0
  6. model-00004-of-00194.safetensors +3 -0
  7. model-00005-of-00194.safetensors +3 -0
  8. model-00006-of-00194.safetensors +3 -0
  9. model-00007-of-00194.safetensors +3 -0
  10. model-00008-of-00194.safetensors +3 -0
  11. model-00009-of-00194.safetensors +3 -0
  12. model-00010-of-00194.safetensors +3 -0
  13. model-00011-of-00194.safetensors +3 -0
  14. model-00012-of-00194.safetensors +3 -0
  15. model-00013-of-00194.safetensors +3 -0
  16. model-00014-of-00194.safetensors +3 -0
  17. model-00015-of-00194.safetensors +3 -0
  18. model-00016-of-00194.safetensors +3 -0
  19. model-00017-of-00194.safetensors +3 -0
  20. model-00018-of-00194.safetensors +3 -0
  21. model-00019-of-00194.safetensors +3 -0
  22. model-00020-of-00194.safetensors +3 -0
  23. model-00021-of-00194.safetensors +3 -0
  24. model-00022-of-00194.safetensors +3 -0
  25. model-00023-of-00194.safetensors +3 -0
  26. model-00024-of-00194.safetensors +3 -0
  27. model-00025-of-00194.safetensors +3 -0
  28. model-00026-of-00194.safetensors +3 -0
  29. model-00027-of-00194.safetensors +3 -0
  30. model-00028-of-00194.safetensors +3 -0
  31. model-00029-of-00194.safetensors +3 -0
  32. model-00030-of-00194.safetensors +3 -0
  33. model-00031-of-00194.safetensors +3 -0
  34. model-00032-of-00194.safetensors +3 -0
  35. model-00033-of-00194.safetensors +3 -0
  36. model-00034-of-00194.safetensors +3 -0
  37. model-00035-of-00194.safetensors +3 -0
  38. model-00036-of-00194.safetensors +3 -0
  39. model-00037-of-00194.safetensors +3 -0
  40. model-00038-of-00194.safetensors +3 -0
  41. model-00039-of-00194.safetensors +3 -0
  42. model-00040-of-00194.safetensors +3 -0
  43. model-00041-of-00194.safetensors +3 -0
  44. model-00042-of-00194.safetensors +3 -0
  45. model-00043-of-00194.safetensors +3 -0
  46. model-00044-of-00194.safetensors +3 -0
  47. model-00045-of-00194.safetensors +3 -0
  48. model-00046-of-00194.safetensors +3 -0
  49. model-00047-of-00194.safetensors +3 -0
  50. model-00048-of-00194.safetensors +3 -0
config.json CHANGED
@@ -2,52 +2,15 @@
2
  "architectures": [
3
  "ArcticForCausalLM"
4
  ],
5
- "attention_dropout": 0,
6
  "auto_map": {
7
  "AutoConfig": "configuration_arctic.ArcticConfig",
8
  "AutoModel": "modeling_arctic.ArcticModel",
9
  "AutoModelForCausalLM": "modeling_arctic.ArcticForCausalLM",
10
  "AutoModelForSequenceClassification": "modeling_arctic.ArcticForSequenceClassification"
11
  },
 
12
  "bos_token_id": 31998,
13
  "enable_expert_tensor_parallelism": false,
14
- "enc_index": [
15
- 0,
16
- 1,
17
- 2,
18
- 3,
19
- 4,
20
- 5,
21
- 6,
22
- 7,
23
- 8,
24
- 9,
25
- 10,
26
- 11,
27
- 12,
28
- 13,
29
- 14,
30
- 15,
31
- 16,
32
- 17,
33
- 18,
34
- 19,
35
- 20,
36
- 21,
37
- 22,
38
- 23,
39
- 24,
40
- 25,
41
- 26,
42
- 27,
43
- 28,
44
- 29,
45
- 30,
46
- 31,
47
- 32,
48
- 33,
49
- 34
50
- ],
51
  "eos_token_id": 31999,
52
  "hidden_act": "silu",
53
  "hidden_size": 7168,
@@ -64,7 +27,7 @@
64
  "num_attention_heads": 56,
65
  "num_experts_per_tok": 2,
66
  "num_hidden_layers": 35,
67
- "num_key_value_heads": 56,
68
  "num_local_experts": 128,
69
  "parallel_attn_mlp_res": true,
70
  "quantization": null,
@@ -74,7 +37,7 @@
74
  "sliding_window": null,
75
  "tie_word_embeddings": false,
76
  "torch_dtype": "bfloat16",
77
- "transformers_version": "4.39.0.dev0",
78
  "use_cache": true,
79
  "use_residual": true,
80
  "vocab_size": 32000
 
2
  "architectures": [
3
  "ArcticForCausalLM"
4
  ],
 
5
  "auto_map": {
6
  "AutoConfig": "configuration_arctic.ArcticConfig",
7
  "AutoModel": "modeling_arctic.ArcticModel",
8
  "AutoModelForCausalLM": "modeling_arctic.ArcticForCausalLM",
9
  "AutoModelForSequenceClassification": "modeling_arctic.ArcticForSequenceClassification"
10
  },
11
+ "attention_dropout": 0,
12
  "bos_token_id": 31998,
13
  "enable_expert_tensor_parallelism": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "eos_token_id": 31999,
15
  "hidden_act": "silu",
16
  "hidden_size": 7168,
 
27
  "num_attention_heads": 56,
28
  "num_experts_per_tok": 2,
29
  "num_hidden_layers": 35,
30
+ "num_key_value_heads": 8,
31
  "num_local_experts": 128,
32
  "parallel_attn_mlp_res": true,
33
  "quantization": null,
 
37
  "sliding_window": null,
38
  "tie_word_embeddings": false,
39
  "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.40.0.dev0",
41
  "use_cache": true,
42
  "use_residual": true,
43
  "vocab_size": 32000
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 31998,
4
  "eos_token_id": 31999,
5
- "transformers_version": "4.39.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 31998,
4
  "eos_token_id": 31999,
5
+ "transformers_version": "4.40.0.dev0"
6
  }
model-00001-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6b3b661afba0f1d3c81c6a13d33c32a8970671e29c167bef5eb880891d36cb
3
+ size 4949025248
model-00002-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffaaea90765ed446108d6ad626823776ab1219c4e1193c1fe62bfc6829de3003
3
+ size 4950860888
model-00003-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525b2c3078d389c0165319d76134c9b09df53dba33fd28512b6a6f84a320ba59
3
+ size 4950860888
model-00004-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6942a6252289ff0c875005c20bd4ae03afc459207d6d645105ad521085d246
3
+ size 4950860888
model-00005-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780b63b65fe941603685c2d77e41e7741ca44b0c50ef063b96fc4afa843fc6f1
3
+ size 4950860936
model-00006-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99679d8e27845bb97ca6b0584cc397a35f1adcd55697417e4daea06560b3e137
3
+ size 4938059088
model-00007-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a9d980f33b215cf1c8a0e4c1efaa504bb5891b871c8d208971e7f651c3b77e
3
+ size 4950860880
model-00008-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c597884b4fdd066ad311cc71d4935ba8c16b806e892f4252b55c60877ffe81c6
3
+ size 4950860888
model-00009-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e115943add33c745b7d05721c3a18ae343c92c51bf10d236ee2f9ffff6df88
3
+ size 4950860888
model-00010-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a7c99a6e28c3f34639efff064cd7b71e28848c383477b4a358d08bf3beb017
3
+ size 4950860896
model-00011-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cc861d96f05c3c23629acf102e78c968f6729b5fb02ef7fe11b6ffad90f894
3
+ size 4950860960
model-00012-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7f34b93e8285791dcda9e4fb62520771619026294bf09018140092a0e920ce
3
+ size 4938059048
model-00013-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81da7d218661db4ba306fe3edb511e651fcc45ff54c92413c8b92fcb17215e3
3
+ size 4950860888
model-00014-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827e4bac4c5f8a8bbece1b90b576c1a9f016898f6dc74e31f101d8a8640ae2ad
3
+ size 4950860888
model-00015-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b18a5d47f134c2d7a86b043c6ff1eabbd63ba50a14d931cc2b37a3090f90531
3
+ size 4950860888
model-00016-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3600ee555b020f99e6de2aa2922793680dc3037dc0f273bcd5683daa06a39cdf
3
+ size 4950860928
model-00017-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5474d2f5c6ee898006bc2e6a6c9d8cbd97719b15f9c9d8120daa472f80595ce7
3
+ size 4938059096
model-00018-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29beb9e4e5a7098e3e88f1df935bfc0fa7286bc5883878656a0e09fd8df24496
3
+ size 4950860880
model-00019-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0718a1ba6e333a06449c8a5b4edb4b2a2e085bf7d38f149efd642a5d84ed5f5
3
+ size 4950860888
model-00020-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8ee3cf56f1a66545d335af2686aec656417b8881b7411e7011a9280acc588f
3
+ size 4950860888
model-00021-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a965babc1a7608f382b22dd5b570e1f6ccb4b0d9c1aab9928751f841b40043
3
+ size 4950860896
model-00022-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd42bb7296c3da84e22799f40cf2eaa4311e9c5d0d30da8f7f29a16a3ed5765
3
+ size 4950860960
model-00023-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5073d62eebf9a4ae235eb416b742da8e22955596008c7274984d6f6e40c43c1a
3
+ size 4938059048
model-00024-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e27ec46a78f76166d67c1af957ef959b7d037844c32a8378d6ff9e131de613
3
+ size 4950860888
model-00025-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a415586e5b318ebd6a2296e1f67743b2887effaf1e5b28db0879b8b03aa4fa
3
+ size 4950860888
model-00026-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4fbe2327ccf34d547e934656bd6306fdf692ed0a46fbc67929282f852abb5f
3
+ size 4950860888
model-00027-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56331dc2e68347f0ca177092e5cfc4a5ee6d9f988eedccf8bc2e743e5de8eb88
3
+ size 4950860928
model-00028-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30174a3c3bab79cb51d17cdc9d091bd344652d2eeb86562e91980def55da1ceb
3
+ size 4938059104
model-00029-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da0d273a14bde6d01539198cab2b52242e50fc983ecc8e9073da0541c3436f90
3
+ size 4950860880
model-00030-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ab38c54bbe674cb018278e495df349ce92af4e572b6a6876d5797620849fc5
3
+ size 4950860888
model-00031-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cf2ba3e32da0c033e789430ecc3540abdeea590db8a68033fa56b6a65a268d
3
+ size 4950860888
model-00032-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6b94ab3e354c934c92c54269e533c1bd10919a2a1cacbcf4263d683f549d96
3
+ size 4950860888
model-00033-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e092aa7afdd2723f72336a4aa06f63aae009408f65242015aa328546dc05eda1
3
+ size 4950860960
model-00034-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806269f07bf9d80b1b14dd3b040eaa5684d0beab4557495d45cc7db907746e6c
3
+ size 4938059056
model-00035-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ce77a3e8bf4c046e10d91b78b3aee5154b776b08ea7db0ffe1849120c531cc
3
+ size 4950860888
model-00036-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d295f0c0b88078ef98d190282ca3263fd4cfc6cd636609bbcd98cbf8a08b73
3
+ size 4950860888
model-00037-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d454f57c7b962680f42bd36de7319f45027418f5b4e843093a8d3bf604c5ad
3
+ size 4950860888
model-00038-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1d1d33c0842d7c5635187b9e29a3f15fe3c7e1548190577e0c5e7238d19eed
3
+ size 4950860928
model-00039-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dddc462bc6c106ad44dbd184a4f6e3b193d030f20f0b5219dbdc14f167f37963
3
+ size 4938059112
model-00040-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835a041b2ccf38998226ea7a1903690ecfbb0edd9b786c7b9cadc98c2f376ec3
3
+ size 4950860872
model-00041-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c159ad01ad2be59a1d3631109ce57d22a2d16cf8e3f2c3aa0358958a5dd263
3
+ size 4950860888
model-00042-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89fb921c670bc7dc8b1d94ffd19f3c20a14fe7613df5e25f577431b5841e424
3
+ size 4950860888
model-00043-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3417b3e2c641ce925c44ffdeece5772c7ce832e164d237009e8c2360a5faf000
3
+ size 4950860888
model-00044-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff844aaae7961c7240a0e260bcfa81975cd61b53c068ce4a5ba085500eaee6c
3
+ size 4950860960
model-00045-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f22daa86c78fd393a6213889079ff588e6db1988c854e7b3793e412e3cddf7
3
+ size 4938059056
model-00046-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57a3680f7fb685e2e20165c5eca5299c9fa168ebe09733a767903509b371c11
3
+ size 4950860888
model-00047-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106f323c866eaf6b29597d22975e3a42605555d6716013aa27faa2ee40a4082a
3
+ size 4950860888
model-00048-of-00194.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea2d67f0cb60ee3a0d8607fef879185339db9416aa6e1b7b8bd231a378c3c81
3
+ size 4950860888