welyjesch commited on
Commit
1b20b41
·
verified ·
1 Parent(s): bdd838c

Upload folder using huggingface_hub

Browse files
cpt_train_dataset.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60cebeb5b7093b4f1b7d01566aa8321e4bf7b01422d8748125fb4cd4f6227d5f
3
- size 87234819
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5383d12081e44f10ea348bf0e2225cf3a6f261bea5c7ad8d17459e9eace0de89
3
+ size 1849241
cpt_train_dataset_shard_0.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b07377423eda2e695146c3b364f4aed74eff053b9871a121effbb3b8d1ac376
3
- size 17510861
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f8113dfd581d92de3c5881e3baebb7f958a7ef19d8857d73acecba38a3dab75
3
+ size 616563
cpt_train_dataset_shard_1.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01d24692b62ea3e266a270c60a4c959a28f661e78b165b601b72d82a1d98fede
3
- size 17472164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b81ccf39e1d711d9a7c235606ae3fbc643a9d927473e1b7119d48d6f0923dd6
3
+ size 618639
cpt_train_dataset_shard_2.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7419d86c431caf8b590f788ac5a2d54d111c8b3a1fb1de6ec39dfb8fb2bb33b8
3
- size 17392999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0560fb355c329ea0ceb1882295ca398fa242a356fc996ecfac1edb7733781b72
3
+ size 614039
merged_tokenizer/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:579a19f2a07b4e0d9a63f31da1d677f2ea7e0dbf8ade390c18fd812e561848f2
3
- size 12391006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6570aa3af565f7ad7ac54096dbd11365d52b1ce4999a6308b7d5a62fda9fa738
3
+ size 12170837
prep_metadata.json CHANGED
@@ -6,16 +6,12 @@
6
  "cpt_shards": [
7
  "/content/qwen3_outputs/assets/cpt_train_dataset_shard_0.json",
8
  "/content/qwen3_outputs/assets/cpt_train_dataset_shard_1.json",
9
- "/content/qwen3_outputs/assets/cpt_train_dataset_shard_2.json",
10
- "/content/qwen3_outputs/assets/cpt_train_dataset_shard_3.json",
11
- "/content/qwen3_outputs/assets/cpt_train_dataset_shard_4.json"
12
  ],
13
  "sft_shards": [
14
  "/content/qwen3_outputs/assets/sft_train_dataset_shard_0.json",
15
  "/content/qwen3_outputs/assets/sft_train_dataset_shard_1.json",
16
- "/content/qwen3_outputs/assets/sft_train_dataset_shard_2.json",
17
- "/content/qwen3_outputs/assets/sft_train_dataset_shard_3.json",
18
- "/content/qwen3_outputs/assets/sft_train_dataset_shard_4.json"
19
  ],
20
  "base_model": "Qwen/Qwen3-0.6B-Base"
21
  }
 
6
  "cpt_shards": [
7
  "/content/qwen3_outputs/assets/cpt_train_dataset_shard_0.json",
8
  "/content/qwen3_outputs/assets/cpt_train_dataset_shard_1.json",
9
+ "/content/qwen3_outputs/assets/cpt_train_dataset_shard_2.json"
 
 
10
  ],
11
  "sft_shards": [
12
  "/content/qwen3_outputs/assets/sft_train_dataset_shard_0.json",
13
  "/content/qwen3_outputs/assets/sft_train_dataset_shard_1.json",
14
+ "/content/qwen3_outputs/assets/sft_train_dataset_shard_2.json"
 
 
15
  ],
16
  "base_model": "Qwen/Qwen3-0.6B-Base"
17
  }
raw_corpus.txt ADDED
The diff for this file is too large to render. See raw diff
 
sft_train_dataset.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71b441738269577f875c9299eef9bd3c83e5df78eb32826c463db338e057665b
3
- size 99495292
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25f8346ef31667d4c6379a87034843fc4ebd76f66d778e816e039ce5fbbb1b3
3
+ size 5156314
sft_train_dataset_shard_0.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f62fb1d88b0986f47465a98288c51647658166241e4b6d00504e8fba0ca0c3f
3
- size 20430027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa0c97f20ff41828ca81fa3798ba24664aba94a6e2132d22c3b3866055193fd
3
+ size 1718916
sft_train_dataset_shard_1.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5248eeb8e2c4b1a828e91c15198d0e85a75aadeca59a3f5057588be5e479e0b7
3
- size 20552939
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be177525772cce0e29bc7f6b202aee7cf341081e49c22b7e2548917cc079a69e
3
+ size 1722554
sft_train_dataset_shard_2.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b2c326a96705932dd80268e16987e6ae0e8b0483ff835c70c9c766a53154b36
3
- size 19636711
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5cb1de382add810feef2d504cfa1195da2354c7f086eb68813c60bef4d3ed0
3
+ size 1714844
standalone_bpe.json ADDED
The diff for this file is too large to render. See raw diff