jonabur commited on
Commit
9f3d465
1 Parent(s): dc0e31c

add 700B checkpoint

Browse files
README.md CHANGED
@@ -14,7 +14,7 @@ datasets:
14
 
15
  _**NOTE:** This is a **research checkpoint** of a model for which **training has not been completed.** It is being provided in its current state for research and testing purposes. **Care should be taken when using the outputs of the model.** Once pretraining has completed we intend to release additional instruction-tuned and chat-tuned varieties._
16
 
17
- Poro is a 34B parameter decoder-only transformer pretrained on Finnish, English and code. It is being trained on 1 trillion tokens (600 billion as of this release). Poro is a fully open source model and is made available under the Apache 2.0 License.
18
 
19
  Poro was created in a collaboration between [SiloGen](https://www.silo.ai/silogen) from [Silo AI](https://www.silo.ai/), the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
20
 
@@ -48,6 +48,7 @@ Checkpoints are available as branches in the repository. Checkpoints will be re
48
  * [400B](https://huggingface.co/LumiOpen/Poro-34B/tree/400B)
49
  * [500B](https://huggingface.co/LumiOpen/Poro-34B/tree/500B)
50
  * [600B](https://huggingface.co/LumiOpen/Poro-34B/tree/600B)
 
51
 
52
  The transformers library allows you to load a checkpoint from a branch as follows:
53
 
 
14
 
15
  _**NOTE:** This is a **research checkpoint** of a model for which **training has not been completed.** It is being provided in its current state for research and testing purposes. **Care should be taken when using the outputs of the model.** Once pretraining has completed we intend to release additional instruction-tuned and chat-tuned varieties._
16
 
17
+ Poro is a 34B parameter decoder-only transformer pretrained on Finnish, English and code. It is being trained on 1 trillion tokens (700 billion as of this release). Poro is a fully open source model and is made available under the Apache 2.0 License.
18
 
19
  Poro was created in a collaboration between [SiloGen](https://www.silo.ai/silogen) from [Silo AI](https://www.silo.ai/), the [TurkuNLP group](https://turkunlp.org/) of the University of Turku, and [High Performance Language Technologies](https://hplt-project.org/) (HPLT). Training was conducted on the [LUMI supercomputer](https://www.lumi-supercomputer.eu/), using compute resources generously provided by [CSC](https://csc.fi/) - IT Center for Science, Finland.
20
 
 
48
  * [400B](https://huggingface.co/LumiOpen/Poro-34B/tree/400B)
49
  * [500B](https://huggingface.co/LumiOpen/Poro-34B/tree/500B)
50
  * [600B](https://huggingface.co/LumiOpen/Poro-34B/tree/600B)
51
+ * [700B](https://huggingface.co/LumiOpen/Poro-34B/tree/700B)
52
 
53
  The transformers library allows you to load a checkpoint from a branch as follows:
54
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/scratch/project_462000319/general-tools/checkpoints/33B_torch_step143712_bfloat16",
3
  "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
  "BloomForCausalLM"
@@ -20,7 +20,7 @@
20
  "pretraining_tp": 2,
21
  "slow_but_exact": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.35.0",
24
  "use_cache": true,
25
  "vocab_size": 128000
26
  }
 
1
  {
2
+ "_name_or_path": "/scratch/project_462000319/general-tools/checkpoints/33B_torch_step166752_bfloat16",
3
  "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
  "BloomForCausalLM"
 
20
  "pretraining_tp": 2,
21
  "slow_but_exact": false,
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.36.0",
24
  "use_cache": true,
25
  "vocab_size": 128000
26
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 3,
6
- "transformers_version": "4.35.0"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 3,
6
+ "transformers_version": "4.36.0"
7
  }
model-00001-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:122e8a9baec708629e3476dd789bd16a669ceb461c4811af61f8238179892a2c
3
  size 4712820784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad4beef808771cae6edf6f14579dfbff9a40c655f61bb5e8d8575b93c714042a
3
  size 4712820784
model-00002-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2689231237b8bbc0b7d1217690de3d90f859966c6fbb881b0827ee38a79ffdb7
3
  size 4933252680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5382b95e1b9991b956fced7510623a59667404af1086b2d34f1e8237e61580e0
3
  size 4933252680
model-00003-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1db3f74bdf45dd015aff31edc083d1c7b740a2d18d51524ced786f5f81dfa19
3
  size 4933252648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64b5a0c8cc2414f9f01f765957db059ed1a81ec0d1887a8ab01c36036641c16
3
  size 4933252648
model-00004-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b006e28ebe97c8416e90d552838ea6e0bbfae1cdaa9de6ab3287509e0d981fbb
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2612ffbe340c98a35f0f7b8e32a90e3fb35c276ae363d97690b29655b0c0f631
3
  size 4933252728
model-00005-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0486a7f51f2e5a83383c4f436082e6b4e0320642ddda25aaa791b5030e3e4e70
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec36fa7fe18e7e3c115cf1d8b6a52ae93fa9ed8aae675f87b5ed32725b4a340a
3
  size 4933252728
model-00006-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aec6faf7cbeb1a9755844e1e6d888c56e51f9392d7f49110e68c44a4c708383
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4ee77d6ac1264c542039cc432f99786a0fcae796a9f6ec9178a507b77dba86
3
  size 4933252728
model-00007-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5f45a9259e64aad76dbe7e4c586bf6575b54faf0f900fff8a51f17439aed691
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129e11b03118922eb1b24085b08e85af0cd2e73ad6b0e6b1ca8824bb583e3de8
3
  size 4933252728
model-00008-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caa0d3ced1171735eec853bfd05212c5778d7157a89fbfef4f43c1bb353c18d4
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cddd448da7da54664abc79ab3d6001de64b586e07d6641b2c5923a950be538
3
  size 4933252728
model-00009-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bce6dd88d67171b89babd472dda1a3e5bc3af8ef0b0714cb96a11090bb28df7
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e7b1db555170ecf0095cc25cdcd3d5d683d42c5dbb444286c226af1e8750ea
3
  size 4933252728
model-00010-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc28d2be3e6ae211f747c1b9838e357f273b8944b7f3c6e08472546607383554
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d901daa5518111d19ad3b34fe83480fce97bc33c23cd1414e89dcee1a6a0883
3
  size 4933252728
model-00011-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fb88920dd5b872dadc35b0b0dfceb7196bc00c1e5f29d463a932de912ab9a58
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c89c4ba9550cee307b3614361f04dc7c06d10e0b9d9b74e4eade02bfb673768
3
  size 4933252728
model-00012-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bf10456a80691d04b4d9734d7adf3c62437b15720c61023d76d013b77f0f6cc
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf43f8744a3f9a1d4d85d2c4912cc7c8eb8857fa1896319df0dfe75ffdf8166
3
  size 4933252728
model-00013-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:792d81f54fc1398d38e7cb415b3ee96c08944b12dc7cec79ea9e8b49546581e6
3
  size 4933252728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba623da877b94b34c6194db40b4ef1ba97331cc37e23c72e6a9cdfca4d8b547
3
  size 4933252728
model-00014-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76bdca2059826a6775c40650558217028f37ad640eef2039a952eac7ba613baa
3
  size 4522124144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ddfdb7ce089a24e81758eddf768a7057ba3bd6dc74c33182414b3ee640d103
3
  size 4522124144