bloomchat-deepspeed-inference first version
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- config.json +26 -0
- ds_inference_config.json +1 -0
- non-tp.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -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
- tp_04_00.pt +3 -0
- tp_04_01.pt +3 -0
- tp_04_02.pt +3 -0
- tp_04_03.pt +3 -0
- tp_04_04.pt +3 -0
- tp_04_05.pt +3 -0
- tp_04_06.pt +3 -0
- tp_04_07.pt +3 -0
- tp_05_00.pt +3 -0
- tp_05_01.pt +3 -0
- tp_05_02.pt +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_residual_connection_post_layernorm": false,
|
3 |
+
"architectures": [
|
4 |
+
"BloomModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"attention_softmax_in_fp32": false,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_dropout": 0.0,
|
11 |
+
"hidden_size": 14336,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"masked_softmax_fusion": true,
|
15 |
+
"model_type": "bloom",
|
16 |
+
"n_head": 112,
|
17 |
+
"n_layer": 70,
|
18 |
+
"pad_token_id": 3,
|
19 |
+
"pretraining_tp": 4,
|
20 |
+
"return_dict": false,
|
21 |
+
"slow_but_exact": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.27.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250880
|
26 |
+
}
|
ds_inference_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"type": "BLOOM", "checkpoints": {"non_tp": ["non-tp.pt"], "tp": ["tp_00_00.pt", "tp_01_00.pt", "tp_02_00.pt", "tp_03_00.pt", "tp_04_00.pt", "tp_05_00.pt", "tp_06_00.pt", "tp_07_00.pt", "tp_00_01.pt", "tp_01_01.pt", "tp_02_01.pt", "tp_03_01.pt", "tp_04_01.pt", "tp_05_01.pt", "tp_06_01.pt", "tp_07_01.pt", "tp_00_02.pt", "tp_01_02.pt", "tp_02_02.pt", "tp_03_02.pt", "tp_04_02.pt", "tp_05_02.pt", "tp_06_02.pt", "tp_07_02.pt", "tp_00_03.pt", "tp_01_03.pt", "tp_02_03.pt", "tp_03_03.pt", "tp_04_03.pt", "tp_05_03.pt", "tp_06_03.pt", "tp_07_03.pt", "tp_00_04.pt", "tp_01_04.pt", "tp_02_04.pt", "tp_03_04.pt", "tp_04_04.pt", "tp_05_04.pt", "tp_06_04.pt", "tp_07_04.pt", "tp_00_05.pt", "tp_01_05.pt", "tp_02_05.pt", "tp_03_05.pt", "tp_04_05.pt", "tp_05_05.pt", "tp_06_05.pt", "tp_07_05.pt", "tp_00_06.pt", "tp_01_06.pt", "tp_02_06.pt", "tp_03_06.pt", "tp_04_06.pt", "tp_05_06.pt", "tp_06_06.pt", "tp_07_06.pt", "tp_00_07.pt", "tp_01_07.pt", "tp_02_07.pt", "tp_03_07.pt", "tp_04_07.pt", "tp_05_07.pt", "tp_06_07.pt", "tp_07_07.pt"]}, "version": 1.0, "parallelization": "tp", "tp_size": 8, "dtype": "float16"}
|
non-tp.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feee1afa69a85d153ac209174f243fc1ce38d778f982981dd2bba7dc6c32e9f7
|
3 |
+
size 7193348595
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
|
3 |
+
size 14500471
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"padding_side": "left",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
+
"tokenizer_class": "BloomTokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
tp_00_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3495d0837374b58698914ef6cb583e642fcb2c6ca03d0f26067b6ec37e4bf504
|
3 |
+
size 5139738277
|
tp_00_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:908023ffbef8a5424ec3c29a28bd2e0699e42b61dd94a8abe5aded0e81a8467d
|
3 |
+
size 5550854247
|
tp_00_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49d5d7b57bc0cc87258e63a0ec7f1b35ee4a60203e5be756b95939b8ea3f548
|
3 |
+
size 5499502189
|
tp_00_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fe81283c5d16706e8eb07adfe85f6206ca3e588c804b031172fc9e3fa30d0f2
|
3 |
+
size 5550872067
|
tp_00_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d94560c22cdd68864513885ef8b48ae6a8bf3b2c250e02772d387b745bb05ece
|
3 |
+
size 5396741705
|
tp_00_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aad6d81c40580bf1e61c75b61b4723c03195e7c647672f00a103dbb3792ae75
|
3 |
+
size 5550854035
|
tp_00_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c754b5253a2d613c3e3aada7ca47bb9490cc889feca42bdb1a91f22d4bfa51b
|
3 |
+
size 5550854087
|
tp_00_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36f5b169d738ae15a7d049cb9d06e78a64aa5f2922fdd679fbb24de79dbc3e15
|
3 |
+
size 4934118061
|
tp_01_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcd244f1a73828ca52c1bc01738c2ebb6bb90753b396688e9159462fa3efbec7
|
3 |
+
size 5139738277
|
tp_01_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b22ccef6ee54a0a461c093530a4f593ab8a7334fe5595b18a43d5c66a1a5e448
|
3 |
+
size 5550854247
|
tp_01_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b6d40e2c8f9ceb681e9a6759cc30016b9334bccae9dd756772af53bfe2140d1
|
3 |
+
size 5499502189
|
tp_01_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c82a322eb3a1a942335350156fb0482f26d07adf4fd7eec4a5fee4656189c8c6
|
3 |
+
size 5550872067
|
tp_01_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:029f6494e6dabe0f3d13c5c1da7ef3b2a09f881dd6a44fc563371a94ae75bc44
|
3 |
+
size 5396741705
|
tp_01_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cac6f08396626f878aad16506ba41a34b64d607f95993bc2ee546a59e4849dbf
|
3 |
+
size 5550854035
|
tp_01_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ceb0cf24105947dc8989aa80c8a247b920edf643905bb15557f0a5f76e88fa
|
3 |
+
size 5550854087
|
tp_01_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4d803d50886f4566b927b5e4b71a385e44493146fd26720117471dfc2af9f9e
|
3 |
+
size 4934118061
|
tp_02_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b31fe7c85eece97be1845c49d39ca0582ea0a268a5ae9b4ef4b74d9ab04715b9
|
3 |
+
size 5139738277
|
tp_02_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e87ed19afd25cc5a4291c996034bdf8beba574314259c5067acd40cdc07be1e
|
3 |
+
size 5550854247
|
tp_02_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa47e61791afda61c731bf56bf528baedecdb39d93c46066272b5681f90bca1a
|
3 |
+
size 5499502189
|
tp_02_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dfc7e54afaf983f1d804d9e3ad8201362dbb390944ed57f4e48a55cbee5c3b1
|
3 |
+
size 5550872067
|
tp_02_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c59a6c4a231a0e664aa2ea7881ea48c8c628acf23a8702a7d4308adf449578
|
3 |
+
size 5396741705
|
tp_02_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:734947ea032475cd50d609fa88297e050685c1bc11576253327e23ef0562dd47
|
3 |
+
size 5550854035
|
tp_02_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c5acbf8fb67a4d191fcdbb5dd1f8191eedba09c5ce7695379f6cc70ed01f051
|
3 |
+
size 5550854087
|
tp_02_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:898a8c75ac4b2e0aeded1a127d00d6869c1934a448d26715834931afd73c2e1b
|
3 |
+
size 4934118061
|
tp_03_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29b1a325c26658f97a920da89b6df14830d0d91c1cf5db4cf64a9736beff9f13
|
3 |
+
size 5139738277
|
tp_03_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a232dba7842038ba8e606973ada40314617de169d1632ec982b4bbf28305998e
|
3 |
+
size 5550854247
|
tp_03_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0479c307563ddd29f62552b7074d9d1638e9b35e68a2e5be6ea15330ff451b88
|
3 |
+
size 5499502189
|
tp_03_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57bb555f9f21f55c5089651ccf84ab0a53b710d2c344d4776b8d44fc328e2bcb
|
3 |
+
size 5550872067
|
tp_03_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d5cb0355584090d6fdd4ac77f177ca124a4d51d38913f628aa713688e7780d
|
3 |
+
size 5396741705
|
tp_03_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b3091cc6a024ed6cf0d3d30bdbc82ae4b3fc8c38fc5499ae53fbe00de65f7a8
|
3 |
+
size 5550854035
|
tp_03_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b70ef580e49a67cfa69d50cc205cd69321f9b5d6ec8e4cfb8c2f09fe92218b26
|
3 |
+
size 5550854087
|
tp_03_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80e1bddfa1c857e9842c34ce2626f3ce722d2cb3e8e0d58e2ee685afe7172888
|
3 |
+
size 4934118061
|
tp_04_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6be5a769e49cfc3d575f0eca9aa2aa17d4326439c81580e732bac1192ed250a1
|
3 |
+
size 5139738277
|
tp_04_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c83ae11eaf3147f63d7b465be7014368719e4d38bd1fcd53444684385af31643
|
3 |
+
size 5550854247
|
tp_04_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:479d8a96ad62871e95a5a145afc25634aa4c3fcba386ee586acae664c6d90256
|
3 |
+
size 5499502189
|
tp_04_03.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b988e3f50c415125757f959fc7982c1b336d728a26bdf204c09e3275a6a793
|
3 |
+
size 5550872067
|
tp_04_04.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:999ba8850a1d06d99ab518fe2a264ce4855bcd894502291948faee9faf8f0202
|
3 |
+
size 5396741705
|
tp_04_05.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a7b68aa046e81e3bde969666959b35c060855fad28e5e2b17a1ca12610be705
|
3 |
+
size 5550854035
|
tp_04_06.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f0c57686a2040b73a7782bfc2d79a141cff5bf7da795d3b58314a06afaa2d15
|
3 |
+
size 5550854087
|
tp_04_07.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:613b53d6aad76f269d765be9d299344d085bfb19c696fc96e072f4a6dc9958dd
|
3 |
+
size 4934118061
|
tp_05_00.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4354c25c7638b63f127ce5ecde67ce9c1c5cffea2752532aa18fd6c98b92f42
|
3 |
+
size 5139738277
|
tp_05_01.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99c079a4b5223b36203a07dcf31273e24a9fb03161ecc7a389bb6b6515b37294
|
3 |
+
size 5550854247
|
tp_05_02.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:232d4e30ae8fd95e328c824d9848f41434a6ea71ae388bffb7cedd8d0f6bfacc
|
3 |
+
size 5499502189
|