lucadiliello
commited on
Commit
·
b56a2b4
1
Parent(s):
49d33ed
added tp sharded ckpts
Browse files- config.json +31 -0
- ds_inference_config.json +1 -0
- merges.txt +0 -0
- non-tp.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +41 -0
- tp_00_00.pt +3 -0
- tp_00_01.pt +3 -0
- tp_00_02.pt +3 -0
- tp_00_03.pt +3 -0
- tp_00_04.pt +3 -0
- tp_00_05.pt +3 -0
- tp_00_06.pt +3 -0
- tp_00_07.pt +3 -0
- tp_01_00.pt +3 -0
- tp_01_01.pt +3 -0
- tp_01_02.pt +3 -0
- tp_01_03.pt +3 -0
- tp_01_04.pt +3 -0
- tp_01_05.pt +3 -0
- tp_01_06.pt +3 -0
- tp_01_07.pt +3 -0
- tp_02_00.pt +3 -0
- tp_02_01.pt +3 -0
- tp_02_02.pt +3 -0
- tp_02_03.pt +3 -0
- tp_02_04.pt +3 -0
- tp_02_05.pt +3 -0
- tp_02_06.pt +3 -0
- tp_02_07.pt +3 -0
- tp_03_00.pt +3 -0
- tp_03_01.pt +3 -0
- tp_03_02.pt +3 -0
- tp_03_03.pt +3 -0
- tp_03_04.pt +3 -0
- tp_03_05.pt +3 -0
- tp_03_06.pt +3 -0
- tp_03_07.pt +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-30b",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": true,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 28672,
|
16 |
+
"hidden_size": 7168,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 56,
|
23 |
+
"num_hidden_layers": 48,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"prefix": "</s>",
|
26 |
+
"torch_dtype": "float16",
|
27 |
+
"transformers_version": "4.27.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50272,
|
30 |
+
"word_embed_proj_dim": 7168
|
31 |
+
}
|
ds_inference_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"type": "bloom", "base_dir": "/science/lucadiliello/models/facebook/sharded/opt-30b-deepspeed-inference-fp16-shard-4", "checkpoints": {"non_tp": ["non-tp.pt"], "tp": ["tp_00_00.pt", "tp_01_00.pt", "tp_02_00.pt", "tp_03_00.pt", "tp_00_01.pt", "tp_01_01.pt", "tp_02_01.pt", "tp_03_01.pt", "tp_00_02.pt", "tp_01_02.pt", "tp_02_02.pt", "tp_03_02.pt", "tp_00_03.pt", "tp_01_03.pt", "tp_02_03.pt", "tp_03_03.pt", "tp_00_04.pt", "tp_01_04.pt", "tp_02_04.pt", "tp_03_04.pt", "tp_00_05.pt", "tp_01_05.pt", "tp_02_05.pt", "tp_03_05.pt", "tp_00_06.pt", "tp_01_06.pt", "tp_02_06.pt", "tp_03_06.pt", "tp_00_07.pt", "tp_01_07.pt", "tp_02_07.pt", "tp_03_07.pt"]}, "version": 1.0, "parallelization": "tp", "tp_size": 4, "dtype": "float16"}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
non-tp.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd9d68f2514fff789d00648f4d0773c910b166f5d1e51c54920639b5841b4ad4
|
3 |
+
size 429
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
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 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "</s>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "</s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"pad_token": {
|
23 |
+
"__type": "AddedToken",
|
24 |
+
"content": "<pad>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"padding_side": "left",
|
31 |
+
"special_tokens_map_file": null,
|
32 |
+
"tokenizer_class": "GPT2Tokenizer",
|
33 |
+
"unk_token": {
|
34 |
+
"__type": "AddedToken",
|
35 |
+
"content": "</s>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": true,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
}
|
41 |
+
}
|
tp_00_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8e205d8469779a9bca8757ca6e069c45eccc67f40e2f5202d1854a271d94e85
|
3 |
+
size 2394937261
|
tp_00_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:527bdf2d63d50338fbba2a380a010e268f98e7a768c3a66b30f6f3b687c1715e
|
3 |
+
size 1850399589
|
tp_00_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa8cd879662ef124db2674790355be11cfd9df56ec64a3235caec2cc7e31749
|
3 |
+
size 1953146083
|
tp_00_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad457a0a3c195ff8457f55924894ab98e7f1d1e6d2315222b01d54a3bb083fd5
|
3 |
+
size 1850399653
|
tp_00_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:610041d128b271529e13a8ae6988c2b4d385ea607247f83a30c8209e01f783dd
|
3 |
+
size 1953146083
|
tp_00_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da9c37b664a1bf9bd5dbeab764a6233def31ad4cb4766b8787bd682168f3c4e9
|
3 |
+
size 1850399653
|
tp_00_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af9e86123c1afddbcb521cacd73e39c3f6eaf04bbe122da52c4b779d6b48550d
|
3 |
+
size 1850399653
|
tp_00_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3086246cb9e764cb1d2a130a597529f2fe684c650a7b0ad4bb05d20fd2a394f7
|
3 |
+
size 2571070055
|
tp_01_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d572ffeac54193a7b6e7371bebb8951f6ae5a67e15f546c132d38839b5adbb6
|
3 |
+
size 2394937261
|
tp_01_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1088bf9b274b43504c0a3fe8d1023c4daa2ef2f07150807cbc7f3ce3cd12db97
|
3 |
+
size 1850399589
|
tp_01_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1787ce3f05c49f68417f61eac031d8a926cf028a16b0b65989346d9ed1c1b624
|
3 |
+
size 1953146083
|
tp_01_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84fadb776cf740c011c1df4f3136474350888ef6de897a780d608fd066fb76e5
|
3 |
+
size 1850399653
|
tp_01_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22a2d97e606bb2ffa9804557c667ff6216539bb752b2644f8874cd1dcfa580b4
|
3 |
+
size 1953146083
|
tp_01_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dd32f993c2fd513cdc8ca6e4526c97fcab4f332d6e018eda4a820b3818c6bfd
|
3 |
+
size 1850399653
|
tp_01_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02dd9da998e78bcbcc25d944ee8c8795668e4b89573417a991b19cc611bb4b49
|
3 |
+
size 1850399653
|
tp_01_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cde590b0f0dfc650fe3393e278f7f5a8bde781c953ea46e08eba86eeaca73b52
|
3 |
+
size 2571070055
|
tp_02_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fceac84838f487c02dc7bc70e861035ff1a2aa7bcdc9aa4c207fd3c2348881e
|
3 |
+
size 2394937261
|
tp_02_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2b26abaec74e7a722640aba0b83721545bc3cad61622af29a19b3cdc7f2e2fc
|
3 |
+
size 1850399589
|
tp_02_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde5e9d44aa9b76d85dec01856759b3947d0a1b5282df3a2b7984d46aefd018f
|
3 |
+
size 1953146083
|
tp_02_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7acc69f5c1f983c6921f9175ee392009575cfb7f03a2cd49b42e8a3fb4b4feea
|
3 |
+
size 1850399653
|
tp_02_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f5525db8cfe00775a7da57000fd6d8bc91c71d675f1c4122659ab055785286c
|
3 |
+
size 1953146083
|
tp_02_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaa21a6c3e438ff7df0edc9f3c1397fc40962cb2af18c518015ca93c017a52d8
|
3 |
+
size 1850399653
|
tp_02_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad0b1815c939b64f1d4b313ad648af8a6e40ef968927c982d41f425421304fb8
|
3 |
+
size 1850399653
|
tp_02_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3852a827e1e06bf28b1fcf0c8ba32bb43c877d79d6126c98c51e3a2be4a3a7
|
3 |
+
size 2571070055
|
tp_03_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:060ec7d7ef055624125869db50dd61bbe6d14e7099fa0854b8d20e0d108e5f01
|
3 |
+
size 2394937261
|
tp_03_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e92a12431c7916534c49c2b29bbbaa1f63afc10736ffff7aaf03d99c50e643f9
|
3 |
+
size 1850399589
|
tp_03_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7fabd5b3bd19e863502dffe0cbad42c1562e896568382523f8c8224d81b3a66
|
3 |
+
size 1953146083
|
tp_03_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f4eb706115bd32b884bf651ff407d45b5a058d41b4d07b46a5132c118d9e198
|
3 |
+
size 1850399653
|
tp_03_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ab7b60fc810366d625fc34db51a0ca18f7bdebc6f5f3603970618e3bfe45122
|
3 |
+
size 1953146083
|
tp_03_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c970c0c640b8f7165471ac54d2182ba8ac7fe9d1563d356769de99ebee1ef357
|
3 |
+
size 1850399653
|
tp_03_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7f1f1871d93ccd54c1b4aabb27d17cb679615b34b1586ade13a377cad4876f2
|
3 |
+
size 1850399653
|
tp_03_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ab883b696b7981a14f997b4528d738c587ac4e66690a350a526a1e38793d90
|
3 |
+
size 2571070055
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|