pietrolesci
commited on
Upload folder using huggingface_hub
Browse files- .gitattributes +8 -0
- _bpe_finewebedu_2024-09-04T12-59-54/all_merges.jsonl +0 -0
- _bpe_finewebedu_2024-09-04T12-59-54/implemented_merges.jsonl +3 -0
- _bpe_finewebedu_2024-09-04T12-59-54/metadata.yaml +3 -0
- _bpe_finewebedu_2024-09-04T12-59-54/tokenizer.json +3 -0
- _bpe_minipile_2024-09-22T17-58-54/all_merges.jsonl +0 -0
- _bpe_minipile_2024-09-22T17-58-54/implemented_merges.jsonl +3 -0
- _bpe_minipile_2024-09-22T17-58-54/metadata.yaml +3 -0
- _bpe_minipile_2024-09-22T17-58-54/tokenizer.json +3 -0
- bpe_finewebedu_2024-10-11T20-50-21/all_merges.jsonl +0 -0
- bpe_finewebedu_2024-10-11T20-50-21/implemented_merges.jsonl +3 -0
- bpe_finewebedu_2024-10-11T20-50-21/metadata.yaml +3 -0
- bpe_finewebedu_2024-10-11T20-50-21/tokenizer.json +3 -0
- bpe_minipile_2024-10-11T11-23-27/all_merges.jsonl +0 -0
- bpe_minipile_2024-10-11T11-23-27/implemented_merges.jsonl +3 -0
- bpe_minipile_2024-10-11T11-23-27/metadata.yaml +3 -0
- bpe_minipile_2024-10-11T11-23-27/tokenizer.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,11 @@ 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 |
+
_bpe_finewebedu_2024-09-04T12-59-54/implemented_merges.jsonl filter=lfs diff=lfs merge=lfs -text
|
37 |
+
_bpe_finewebedu_2024-09-04T12-59-54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
38 |
+
_bpe_minipile_2024-09-22T17-58-54/implemented_merges.jsonl filter=lfs diff=lfs merge=lfs -text
|
39 |
+
_bpe_minipile_2024-09-22T17-58-54/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
40 |
+
bpe_finewebedu_2024-10-11T20-50-21/implemented_merges.jsonl filter=lfs diff=lfs merge=lfs -text
|
41 |
+
bpe_finewebedu_2024-10-11T20-50-21/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
42 |
+
bpe_minipile_2024-10-11T11-23-27/implemented_merges.jsonl filter=lfs diff=lfs merge=lfs -text
|
43 |
+
bpe_minipile_2024-10-11T11-23-27/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
_bpe_finewebedu_2024-09-04T12-59-54/all_merges.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
_bpe_finewebedu_2024-09-04T12-59-54/implemented_merges.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:805bb4a844ee15c72279151e0780ab9460372977a76d027c52e9f06cde0f7359
|
3 |
+
size 35344669
|
_bpe_finewebedu_2024-09-04T12-59-54/metadata.yaml
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
max_vocab_size: 320000
|
2 |
+
num_docs: 9500000
|
3 |
+
eos_token: <|endoftext|>
|
_bpe_finewebedu_2024-09-04T12-59-54/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9650d2502332e2053ba5ae5b314325089f715e226b3d1503202429eaedc91cc0
|
3 |
+
size 23598133
|
_bpe_minipile_2024-09-22T17-58-54/all_merges.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
_bpe_minipile_2024-09-22T17-58-54/implemented_merges.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ace3f08cd83828046e11c288e4ee0beeb265898347a41b0b9521426a1a412da8
|
3 |
+
size 35047130
|
_bpe_minipile_2024-09-22T17-58-54/metadata.yaml
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
max_vocab_size: 320000
|
2 |
+
num_docs: 1000000
|
3 |
+
eos_token: <|endoftext|>
|
_bpe_minipile_2024-09-22T17-58-54/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90be5b2ce1a846fcf10b8e05263095075504f855a8a566a4efa39354141fdf83
|
3 |
+
size 23599177
|
bpe_finewebedu_2024-10-11T20-50-21/all_merges.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
bpe_finewebedu_2024-10-11T20-50-21/implemented_merges.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fe2934f2213f62c0a4640d5ce8fb608932c842afda7747d0d232a2e125df535
|
3 |
+
size 35464616
|
bpe_finewebedu_2024-10-11T20-50-21/metadata.yaml
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
max_vocab_size: 320000
|
2 |
+
num_docs: 20000000
|
3 |
+
eos_token: <|endoftext|>
|
bpe_finewebedu_2024-10-11T20-50-21/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32cf9af0b7730c3c70e70c710850ce5d2aa12c9f871d13078e4f0053c009b31c
|
3 |
+
size 23596285
|
bpe_minipile_2024-10-11T11-23-27/all_merges.jsonl
ADDED
The diff for this file is too large to render.
See raw diff
|
|
bpe_minipile_2024-10-11T11-23-27/implemented_merges.jsonl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10c86b1954635fa7975e6f70b69c1bd3c996714dd775c2a0710d490b5e8404ac
|
3 |
+
size 35288764
|
bpe_minipile_2024-10-11T11-23-27/metadata.yaml
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
max_vocab_size: 320000
|
2 |
+
num_docs: 1000000
|
3 |
+
eos_token: <|endoftext|>
|
bpe_minipile_2024-10-11T11-23-27/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b597d8e1fa7b685bfda953a15e6981be9ea03e56f008c6cb521caf28d0a72d6
|
3 |
+
size 23777543
|