Skip to page content
SAVRN
Search Plan a project

Dataset

fineweb-124m-pretraining

by Liangzhi Li Liangzhi-Li/fineweb-124m-pretraining

Training text, token files and checkpoints of small (124-million-parameter) Llama-architecture language models trained on FineWeb.

Rows1,234,391
Configurations1
Size107.8 GB
Licenseodc-by
AccessPublicly accessible
Monthly Downloads—

Dataset Card

By Liangzhi Li, published under odc-by, revision aedb027944dc.

FineWeb 124M pretraining material

Training text, token files and checkpoints of small (124-million-parameter) Llama-architecture language models trained on FineWeb.

Folder Contents
corpora/fineweb/ Shards of FineWeb as released (fields text, id, url, dump, date, language_score), named by Common Crawl dump: dumps of 2019–2021 and of 2024–2025.
corpora/cosmopedia/ Shards of Cosmopedia.
tokens/gpt2/ fineweb_2019-2021.bin: the 2019–2021 FineWeb shards tokenized with the GPT-2 BPE; cosmopedia.bin: the Cosmopedia shards tokenized likewise; streams/: further token streams of FineWeb 2019–2021 text. Every file is a flat array of uint16 token ids; in fineweb_2019-2021.bin and cosmopedia.bin every document ends with token 50256. fineweb_2019-2021.meta.jsonl.gz gives, per document, its position, token count and FineWeb id, url and dump.
tokens/gpt-neox/streams/ Token streams of FineWeb 2019–2021 text with the GPT-NeoX tokenizer (as used by Pythia), uint16.
checkpoints/llama-124m/base/seed1–seed8/ Models trained from scratch on 1.5 billion tokens of FineWeb 2019–2021, one per seed (final/, and for seeds 1–4 also after about 495 and 1,005 million tokens).
checkpoints/llama-124m/runs/run_NNN/ Further training runs of the same architecture (weights only).

Checkpoints

Every checkpoint folder holds model.safetensors (float32) and config.json for transformers' LlamaForCausalLM: 12 layers, hidden size 768, 12 attention heads, MLP size 2048, context 2048, vocabulary 50,304 (the GPT-2 vocabulary padded), RMSNorm, rotary embeddings (θ = 10,000), input and output embeddings tied.

from huggingface_hub import snapshot_download
from transformers import AutoTokenizer, LlamaForCausalLM

sub = "checkpoints/llama-124m/base/seed1/final"
d = snapshot_download("Liangzhi-Li/fineweb-124m-pretraining", repo_type="dataset", allow_patterns=f"{sub}/*")
model = LlamaForCausalLM.from_pretrained(f"{d}/{sub}")
tok = AutoTokenizer.from_pretrained("gpt2")

Training of the base models: AdamW, learning rate 6e-4 with 300 warm-up steps and cosine decay to 6e-5, weight decay 0.1, gradient clipping 1.0, 524,288 tokens per step, 2,861 steps.

Licences

FineWeb: ODC-By 1.0, subject to the Common Crawl terms of use. Cosmopedia: Apache-2.0. Token files derived from them carry the same terms. Checkpoints: CC BY 4.0.

Structure

default 1,234,391 rows

SplitRowsSize
train1,234,3915.0 GB
textstringidstringsrc_configstring

Details

Repository
Liangzhi-Li/fineweb-124m-pretraining
Publisher
Liangzhi Li
Task category
Not stated by the source
Tags
fineweb, pretraining, language-modeling
Size category
1B<n<10B
Languages
en
Revision
aedb027944dca4b9a29a22fc089fe029d199fcb1
Last updated
2026-10-16

Files

377 files, 107.8 GB in total.

Data215 files · 27.0 GB
Documentation1 file · 2.7 KB
Other160 files · 80.8 GB
Repository1 file · 2.5 KB
Every file
FileTypeSizeSHA-256
checkpoints/llama-124m/base/seed1/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed1/tokens_0495M/config.jsonData550 B—
checkpoints/llama-124m/base/seed1/tokens_1005M/config.jsonData550 B—
checkpoints/llama-124m/base/seed2/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed2/tokens_0495M/config.jsonData550 B—
checkpoints/llama-124m/base/seed2/tokens_1005M/config.jsonData550 B—
checkpoints/llama-124m/base/seed3/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed3/tokens_0495M/config.jsonData550 B—
checkpoints/llama-124m/base/seed3/tokens_1005M/config.jsonData550 B—
checkpoints/llama-124m/base/seed4/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed4/tokens_0495M/config.jsonData550 B—
checkpoints/llama-124m/base/seed4/tokens_1005M/config.jsonData550 B—
checkpoints/llama-124m/base/seed5/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed6/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed7/final/config.jsonData550 B—
checkpoints/llama-124m/base/seed8/final/config.jsonData550 B—
checkpoints/llama-124m/runs/run_001/config.jsonData550 B—
checkpoints/llama-124m/runs/run_002/config.jsonData550 B—
checkpoints/llama-124m/runs/run_003/config.jsonData550 B—
checkpoints/llama-124m/runs/run_004/config.jsonData550 B—
checkpoints/llama-124m/runs/run_005/config.jsonData550 B—
checkpoints/llama-124m/runs/run_006/config.jsonData550 B—
checkpoints/llama-124m/runs/run_007/config.jsonData550 B—
checkpoints/llama-124m/runs/run_008/config.jsonData550 B—
checkpoints/llama-124m/runs/run_009/config.jsonData550 B—
checkpoints/llama-124m/runs/run_010/config.jsonData550 B—
checkpoints/llama-124m/runs/run_011/config.jsonData550 B—
checkpoints/llama-124m/runs/run_012/config.jsonData550 B—
checkpoints/llama-124m/runs/run_013/config.jsonData550 B—
checkpoints/llama-124m/runs/run_014/config.jsonData550 B—
checkpoints/llama-124m/runs/run_015/config.jsonData550 B—
checkpoints/llama-124m/runs/run_016/config.jsonData550 B—
checkpoints/llama-124m/runs/run_017/config.jsonData550 B—
checkpoints/llama-124m/runs/run_018/config.jsonData550 B—
checkpoints/llama-124m/runs/run_019/config.jsonData550 B—
checkpoints/llama-124m/runs/run_020/config.jsonData550 B—
checkpoints/llama-124m/runs/run_021/config.jsonData550 B—
checkpoints/llama-124m/runs/run_022/config.jsonData550 B—
checkpoints/llama-124m/runs/run_023/config.jsonData550 B—
checkpoints/llama-124m/runs/run_024/config.jsonData550 B—
checkpoints/llama-124m/runs/run_025/config.jsonData550 B—
checkpoints/llama-124m/runs/run_026/config.jsonData550 B—
checkpoints/llama-124m/runs/run_027/config.jsonData550 B—
checkpoints/llama-124m/runs/run_028/config.jsonData550 B—
checkpoints/llama-124m/runs/run_029/config.jsonData550 B—
checkpoints/llama-124m/runs/run_030/config.jsonData550 B—
checkpoints/llama-124m/runs/run_031/config.jsonData550 B—
checkpoints/llama-124m/runs/run_032/config.jsonData550 B—
checkpoints/llama-124m/runs/run_033/config.jsonData550 B—
checkpoints/llama-124m/runs/run_034/config.jsonData550 B—
checkpoints/llama-124m/runs/run_035/config.jsonData550 B—
checkpoints/llama-124m/runs/run_036/config.jsonData550 B—
checkpoints/llama-124m/runs/run_037/config.jsonData550 B—
checkpoints/llama-124m/runs/run_038/config.jsonData550 B—
checkpoints/llama-124m/runs/run_039/config.jsonData550 B—
checkpoints/llama-124m/runs/run_040/config.jsonData550 B—
checkpoints/llama-124m/runs/run_041/config.jsonData550 B—
checkpoints/llama-124m/runs/run_042/config.jsonData550 B—
checkpoints/llama-124m/runs/run_043/config.jsonData550 B—
checkpoints/llama-124m/runs/run_044/config.jsonData550 B—
checkpoints/llama-124m/runs/run_045/config.jsonData550 B—
checkpoints/llama-124m/runs/run_046/config.jsonData550 B—
checkpoints/llama-124m/runs/run_047/config.jsonData550 B—
checkpoints/llama-124m/runs/run_048/config.jsonData550 B—
checkpoints/llama-124m/runs/run_049/config.jsonData550 B—
checkpoints/llama-124m/runs/run_050/config.jsonData550 B—
checkpoints/llama-124m/runs/run_051/config.jsonData550 B—
checkpoints/llama-124m/runs/run_052/config.jsonData550 B—
checkpoints/llama-124m/runs/run_053/config.jsonData550 B—
checkpoints/llama-124m/runs/run_054/config.jsonData550 B—
checkpoints/llama-124m/runs/run_055/config.jsonData550 B—
checkpoints/llama-124m/runs/run_056/config.jsonData550 B—
checkpoints/llama-124m/runs/run_057/config.jsonData550 B—
checkpoints/llama-124m/runs/run_058/config.jsonData550 B—
checkpoints/llama-124m/runs/run_059/config.jsonData550 B—
checkpoints/llama-124m/runs/run_060/config.jsonData550 B—
checkpoints/llama-124m/runs/run_061/config.jsonData550 B—
checkpoints/llama-124m/runs/run_062/config.jsonData550 B—
checkpoints/llama-124m/runs/run_063/config.jsonData550 B—
checkpoints/llama-124m/runs/run_064/config.jsonData550 B—
checkpoints/llama-124m/runs/run_065/config.jsonData550 B—
checkpoints/llama-124m/runs/run_066/config.jsonData550 B—
checkpoints/llama-124m/runs/run_067/config.jsonData550 B—
checkpoints/llama-124m/runs/run_068/config.jsonData550 B—
checkpoints/llama-124m/runs/run_069/config.jsonData550 B—
checkpoints/llama-124m/runs/run_070/config.jsonData550 B—
checkpoints/llama-124m/runs/run_071/config.jsonData550 B—
checkpoints/llama-124m/runs/run_072/config.jsonData550 B—
checkpoints/llama-124m/runs/run_073/config.jsonData550 B—
checkpoints/llama-124m/runs/run_074/config.jsonData550 B—
checkpoints/llama-124m/runs/run_075/config.jsonData550 B—
checkpoints/llama-124m/runs/run_076/config.jsonData550 B—
checkpoints/llama-124m/runs/run_077/config.jsonData550 B—
checkpoints/llama-124m/runs/run_078/config.jsonData550 B—
checkpoints/llama-124m/runs/run_079/config.jsonData550 B—
checkpoints/llama-124m/runs/run_080/config.jsonData550 B—
checkpoints/llama-124m/runs/run_081/config.jsonData550 B—
checkpoints/llama-124m/runs/run_082/config.jsonData550 B—
checkpoints/llama-124m/runs/run_083/config.jsonData550 B—
checkpoints/llama-124m/runs/run_084/config.jsonData550 B—
checkpoints/llama-124m/runs/run_085/config.jsonData550 B—
checkpoints/llama-124m/runs/run_086/config.jsonData550 B—
checkpoints/llama-124m/runs/run_087/config.jsonData550 B—
checkpoints/llama-124m/runs/run_088/config.jsonData550 B—
checkpoints/llama-124m/runs/run_089/config.jsonData550 B—
checkpoints/llama-124m/runs/run_090/config.jsonData550 B—
checkpoints/llama-124m/runs/run_091/config.jsonData550 B—
checkpoints/llama-124m/runs/run_092/config.jsonData550 B—
checkpoints/llama-124m/runs/run_093/config.jsonData550 B—
checkpoints/llama-124m/runs/run_094/config.jsonData550 B—
checkpoints/llama-124m/runs/run_095/config.jsonData550 B—
checkpoints/llama-124m/runs/run_096/config.jsonData550 B—
checkpoints/llama-124m/runs/run_097/config.jsonData550 B—
checkpoints/llama-124m/runs/run_098/config.jsonData550 B—
checkpoints/llama-124m/runs/run_099/config.jsonData550 B—
checkpoints/llama-124m/runs/run_100/config.jsonData550 B—
checkpoints/llama-124m/runs/run_101/config.jsonData550 B—
checkpoints/llama-124m/runs/run_102/config.jsonData550 B—
checkpoints/llama-124m/runs/run_103/config.jsonData550 B—
checkpoints/llama-124m/runs/run_104/config.jsonData550 B—
checkpoints/llama-124m/runs/run_105/config.jsonData550 B—
checkpoints/llama-124m/runs/run_106/config.jsonData550 B—
checkpoints/llama-124m/runs/run_107/config.jsonData550 B—
checkpoints/llama-124m/runs/run_108/config.jsonData550 B—
checkpoints/llama-124m/runs/run_109/config.jsonData550 B—
checkpoints/llama-124m/runs/run_110/config.jsonData550 B—
checkpoints/llama-124m/runs/run_111/config.jsonData550 B—
corpora/cosmopedia/train_0000.jsonl.gzData366.3 MBb1d94e6f48db
corpora/cosmopedia/train_0001.jsonl.gzData366.2 MB991e037ca96e
corpora/cosmopedia/train_0002.jsonl.gzData366.2 MBfef2675db737
corpora/cosmopedia/train_0003.jsonl.gzData367.4 MB78e581d9d10f
corpora/cosmopedia/train_0004.jsonl.gzData367.4 MB3b2603250504
corpora/cosmopedia/train_0005.jsonl.gzData367.5 MBc728de1ebb5f
corpora/cosmopedia/train_0006.jsonl.gzData386.4 MBd8d7ace81209
corpora/cosmopedia/train_0007.jsonl.gzData386.5 MB561c65bda09f
corpora/cosmopedia/train_0008.jsonl.gzData386.6 MBea78b8a93cf2
corpora/fineweb/CC-MAIN-2019-04_0000.jsonl.gzData170.2 MBc7c8e7df448e
corpora/fineweb/CC-MAIN-2019-09_0000.jsonl.gzData169.9 MBf5b8b188cf50
corpora/fineweb/CC-MAIN-2019-13_0000.jsonl.gzData169.5 MB309954e371aa
corpora/fineweb/CC-MAIN-2019-18_0000.jsonl.gzData169.5 MB8197b66579d1
corpora/fineweb/CC-MAIN-2019-22_0000.jsonl.gzData169.8 MB371e3e7c5d11
corpora/fineweb/CC-MAIN-2019-26_0000.jsonl.gzData169.5 MBd03438537f6f
corpora/fineweb/CC-MAIN-2019-30_0000.jsonl.gzData169.6 MB66fbf6555114
corpora/fineweb/CC-MAIN-2019-35_0000.jsonl.gzData169.1 MB2531337719dc
corpora/fineweb/CC-MAIN-2019-39_0000.jsonl.gzData169.3 MB4e5fffcfde9d
corpora/fineweb/CC-MAIN-2019-43_0000.jsonl.gzData169.2 MB70c65ff9ef65
corpora/fineweb/CC-MAIN-2019-47_0000.jsonl.gzData169.2 MB352160107a56
corpora/fineweb/CC-MAIN-2019-51_0000.jsonl.gzData169.4 MBcb3e42b105e9
corpora/fineweb/CC-MAIN-2020-05_0000.jsonl.gzData169.0 MB79c3baf2f833
corpora/fineweb/CC-MAIN-2020-10_0000.jsonl.gzData169.6 MB23bb57f9d680
corpora/fineweb/CC-MAIN-2020-16_0000.jsonl.gzData168.6 MB610fc856d4f1
corpora/fineweb/CC-MAIN-2020-24_0000.jsonl.gzData169.5 MBcbbde151f991
corpora/fineweb/CC-MAIN-2020-29_0000.jsonl.gzData168.7 MB2b114b5828d5
corpora/fineweb/CC-MAIN-2020-34_0000.jsonl.gzData168.7 MB2628f9bdd7d4
corpora/fineweb/CC-MAIN-2020-40_0000.jsonl.gzData169.1 MBb73ff9227a10
corpora/fineweb/CC-MAIN-2020-45_0000.jsonl.gzData169.0 MB6b8ecb3f181f
corpora/fineweb/CC-MAIN-2020-50_0000.jsonl.gzData169.0 MB9f2638f08808
corpora/fineweb/CC-MAIN-2021-04_0000.jsonl.gzData168.8 MB55dfd0b840fa
corpora/fineweb/CC-MAIN-2021-10_0000.jsonl.gzData168.2 MB0fe403338284
corpora/fineweb/CC-MAIN-2021-17_0000.jsonl.gzData167.9 MB3ea73b55cde7
corpora/fineweb/CC-MAIN-2021-21_0000.jsonl.gzData167.8 MB3c79fe268a82
corpora/fineweb/CC-MAIN-2021-25_0000.jsonl.gzData167.9 MB4ccd9dbc4b14
corpora/fineweb/CC-MAIN-2021-31_0000.jsonl.gzData167.8 MBce86ba28d232
corpora/fineweb/CC-MAIN-2021-39_0000.jsonl.gzData167.9 MB2cb6dc9e662a
corpora/fineweb/CC-MAIN-2021-43_0000.jsonl.gzData167.9 MB4b9f1c3dcd66
corpora/fineweb/CC-MAIN-2021-49_0000.jsonl.gzData168.0 MBc25888968b74
corpora/fineweb/CC-MAIN-2024-10_0000.jsonl.gzData408.0 MB3b44b3515baf
corpora/fineweb/CC-MAIN-2024-10_0001.jsonl.gzData407.8 MB0b8db5aac8fb
corpora/fineweb/CC-MAIN-2024-10_0002.jsonl.gzData331.3 MB725556ea00a2
corpora/fineweb/CC-MAIN-2024-18_0000.jsonl.gzData407.9 MBdad9a67e4784
corpora/fineweb/CC-MAIN-2024-18_0001.jsonl.gzData407.5 MB2eac59efd83f
corpora/fineweb/CC-MAIN-2024-18_0002.jsonl.gzData331.1 MB41845c867e8d
corpora/fineweb/CC-MAIN-2024-22_0000.jsonl.gzData408.6 MB608ae51a1095
corpora/fineweb/CC-MAIN-2024-22_0001.jsonl.gzData408.1 MB8bdec89098af
corpora/fineweb/CC-MAIN-2024-22_0002.jsonl.gzData331.2 MB1f4089a2e593
corpora/fineweb/CC-MAIN-2024-26_0000.jsonl.gzData407.9 MBcfbf823eefa9
corpora/fineweb/CC-MAIN-2024-26_0001.jsonl.gzData407.9 MBb9c7c89584a0
corpora/fineweb/CC-MAIN-2024-26_0002.jsonl.gzData331.6 MBb9f78ca5cf02
corpora/fineweb/CC-MAIN-2024-30_0000.jsonl.gzData408.2 MBebfbb4a72d65
corpora/fineweb/CC-MAIN-2024-30_0001.jsonl.gzData407.3 MBa2bf6dcad3f8
corpora/fineweb/CC-MAIN-2024-30_0002.jsonl.gzData331.1 MB497db157083e
corpora/fineweb/CC-MAIN-2024-33_0000.jsonl.gzData408.4 MB77f5c185ae1e
corpora/fineweb/CC-MAIN-2024-33_0001.jsonl.gzData408.4 MB24a74062030f
corpora/fineweb/CC-MAIN-2024-33_0002.jsonl.gzData331.8 MBb97cbfff6d69
corpora/fineweb/CC-MAIN-2024-38_0000.jsonl.gzData407.4 MBcaa92102302b
corpora/fineweb/CC-MAIN-2024-38_0001.jsonl.gzData406.8 MB19bc5bfeabac
corpora/fineweb/CC-MAIN-2024-38_0002.jsonl.gzData330.6 MB489c84df69ba
corpora/fineweb/CC-MAIN-2024-42_0000.jsonl.gzData407.1 MB69da2d9d4579
corpora/fineweb/CC-MAIN-2024-42_0001.jsonl.gzData406.9 MBc10c404d3c81
corpora/fineweb/CC-MAIN-2024-42_0002.jsonl.gzData330.7 MB622c04493750
corpora/fineweb/CC-MAIN-2024-46_0000.jsonl.gzData406.3 MB57515d3f92a1
corpora/fineweb/CC-MAIN-2024-46_0001.jsonl.gzData406.4 MBb9a1a37080cd
corpora/fineweb/CC-MAIN-2024-46_0002.jsonl.gzData330.6 MB4178e4575238
corpora/fineweb/CC-MAIN-2024-51_0000.jsonl.gzData408.3 MB180464101310
corpora/fineweb/CC-MAIN-2024-51_0001.jsonl.gzData408.0 MBe8cd25ac89e0
corpora/fineweb/CC-MAIN-2024-51_0002.jsonl.gzData331.5 MB9b6ee2fb3174
corpora/fineweb/CC-MAIN-2025-05_0000.jsonl.gzData406.0 MB098f24e01671
corpora/fineweb/CC-MAIN-2025-05_0001.jsonl.gzData405.6 MB73cb90f2039a
corpora/fineweb/CC-MAIN-2025-05_0002.jsonl.gzData329.6 MBc4c0423d2228
corpora/fineweb/CC-MAIN-2025-08_0000.jsonl.gzData407.0 MBe641e930e481
corpora/fineweb/CC-MAIN-2025-08_0001.jsonl.gzData406.5 MB6b21a0c85653
corpora/fineweb/CC-MAIN-2025-08_0002.jsonl.gzData330.1 MBbf9666d15469
corpora/fineweb/CC-MAIN-2025-13_0000.jsonl.gzData406.2 MBaf48f6ea333a
corpora/fineweb/CC-MAIN-2025-13_0001.jsonl.gzData405.8 MBec3efce87887
corpora/fineweb/CC-MAIN-2025-13_0002.jsonl.gzData329.7 MBca9bb6ab2733
corpora/fineweb/CC-MAIN-2025-18_0000.jsonl.gzData406.5 MB93d351e3f5f8
corpora/fineweb/CC-MAIN-2025-18_0001.jsonl.gzData406.2 MB70daf490f1d2
corpora/fineweb/CC-MAIN-2025-18_0002.jsonl.gzData330.1 MBfbb703069632
corpora/fineweb/CC-MAIN-2025-21_0000.jsonl.gzData406.2 MB2294dd366770
corpora/fineweb/CC-MAIN-2025-21_0001.jsonl.gzData406.0 MBb3469cd5c088
corpora/fineweb/CC-MAIN-2025-21_0002.jsonl.gzData329.8 MBe6c208655811
corpora/fineweb/CC-MAIN-2025-26_0000.jsonl.gzData406.5 MBa9c5891ca157
corpora/fineweb/CC-MAIN-2025-26_0001.jsonl.gzData405.6 MB7fe3f0487704
corpora/fineweb/CC-MAIN-2025-26_0002.jsonl.gzData329.7 MB06bb6c411c17
tokens/gpt2/fineweb_2019-2021.meta.jsonl.gzData241.2 MBd47923fed2fd
README.mdDocumentation2.7 KB—
checkpoints/llama-124m/base/seed1/final/model.safetensorsOther494.4 MB74ebdb53b846
checkpoints/llama-124m/base/seed1/tokens_0495M/model.safetensorsOther494.4 MB177a1e270683
checkpoints/llama-124m/base/seed1/tokens_1005M/model.safetensorsOther494.4 MB73f469b08cd5
checkpoints/llama-124m/base/seed2/final/model.safetensorsOther494.4 MB33f081f3d7cf
checkpoints/llama-124m/base/seed2/tokens_0495M/model.safetensorsOther494.4 MBfe88c1c1e80a
checkpoints/llama-124m/base/seed2/tokens_1005M/model.safetensorsOther494.4 MB38e48f239b05
checkpoints/llama-124m/base/seed3/final/model.safetensorsOther494.4 MBaca1df07cfc9
checkpoints/llama-124m/base/seed3/tokens_0495M/model.safetensorsOther494.4 MBeef5a342beaf
checkpoints/llama-124m/base/seed3/tokens_1005M/model.safetensorsOther494.4 MB3c16a5534d37
checkpoints/llama-124m/base/seed4/final/model.safetensorsOther494.4 MBacb533fcc4a7
checkpoints/llama-124m/base/seed4/tokens_0495M/model.safetensorsOther494.4 MB6e4a757a9199
checkpoints/llama-124m/base/seed4/tokens_1005M/model.safetensorsOther494.4 MBa452976c837f
checkpoints/llama-124m/base/seed5/final/model.safetensorsOther494.4 MB9931b685693c
checkpoints/llama-124m/base/seed6/final/model.safetensorsOther494.4 MBc43694436a86
checkpoints/llama-124m/base/seed7/final/model.safetensorsOther494.4 MBdb9697ee3f09
checkpoints/llama-124m/base/seed8/final/model.safetensorsOther494.4 MB44f6a686857e
checkpoints/llama-124m/runs/run_001/model.safetensorsOther494.4 MBd9140ba31459
checkpoints/llama-124m/runs/run_002/model.safetensorsOther494.4 MB1654f3b030d1
checkpoints/llama-124m/runs/run_003/model.safetensorsOther494.4 MBb3ec5fef701b
checkpoints/llama-124m/runs/run_004/model.safetensorsOther494.4 MB21cce53315da
checkpoints/llama-124m/runs/run_005/model.safetensorsOther494.4 MB1ff4dd0e84b8
checkpoints/llama-124m/runs/run_006/model.safetensorsOther494.4 MB1a60629ee750
checkpoints/llama-124m/runs/run_007/model.safetensorsOther494.4 MBbf3be7c22347
checkpoints/llama-124m/runs/run_008/model.safetensorsOther494.4 MBafb9e36bd21a
checkpoints/llama-124m/runs/run_009/model.safetensorsOther494.4 MBe33e0b4ba9b1
checkpoints/llama-124m/runs/run_010/model.safetensorsOther494.4 MBf3388b23fc85
checkpoints/llama-124m/runs/run_011/model.safetensorsOther494.4 MBdaf85b2cc848
checkpoints/llama-124m/runs/run_012/model.safetensorsOther494.4 MB5319e2b2aa28
checkpoints/llama-124m/runs/run_013/model.safetensorsOther494.4 MB72f61f73e866
checkpoints/llama-124m/runs/run_014/model.safetensorsOther494.4 MBae9d37eac56b
checkpoints/llama-124m/runs/run_015/model.safetensorsOther494.4 MBf460750c89c9
checkpoints/llama-124m/runs/run_016/model.safetensorsOther494.4 MBe1071e60e35b
checkpoints/llama-124m/runs/run_017/model.safetensorsOther494.4 MBc884d9a5abd5
checkpoints/llama-124m/runs/run_018/model.safetensorsOther494.4 MBbbd9ba11e934
checkpoints/llama-124m/runs/run_019/model.safetensorsOther494.4 MB114aebb1e5f2
checkpoints/llama-124m/runs/run_020/model.safetensorsOther494.4 MB5abc755b478c
checkpoints/llama-124m/runs/run_021/model.safetensorsOther494.4 MB41d421c7c5d4
checkpoints/llama-124m/runs/run_022/model.safetensorsOther494.4 MB9478970bae34
checkpoints/llama-124m/runs/run_023/model.safetensorsOther494.4 MBf01322715248
checkpoints/llama-124m/runs/run_024/model.safetensorsOther494.4 MBd24f3c426359
checkpoints/llama-124m/runs/run_025/model.safetensorsOther494.4 MB5f7f834b3209
checkpoints/llama-124m/runs/run_026/model.safetensorsOther494.4 MBaebe6734d593
checkpoints/llama-124m/runs/run_027/model.safetensorsOther494.4 MB8a72d05c0c3d
checkpoints/llama-124m/runs/run_028/model.safetensorsOther494.4 MBc04ae8097cfa
checkpoints/llama-124m/runs/run_029/model.safetensorsOther494.4 MB7f60be46bc7c
checkpoints/llama-124m/runs/run_030/model.safetensorsOther494.4 MB7b358ba370a0
checkpoints/llama-124m/runs/run_031/model.safetensorsOther494.4 MB13c8e9a361c4
checkpoints/llama-124m/runs/run_032/model.safetensorsOther494.4 MB3927dba1603a
checkpoints/llama-124m/runs/run_033/model.safetensorsOther494.4 MB97169adc52c7
checkpoints/llama-124m/runs/run_034/model.safetensorsOther494.4 MB0c19a31ef1e6
checkpoints/llama-124m/runs/run_035/model.safetensorsOther494.4 MBfeca8c88cdbc
checkpoints/llama-124m/runs/run_036/model.safetensorsOther494.4 MB9014312aacbe
checkpoints/llama-124m/runs/run_037/model.safetensorsOther494.4 MB868f4c81f806
checkpoints/llama-124m/runs/run_038/model.safetensorsOther494.4 MB4e3dc7d63828
checkpoints/llama-124m/runs/run_039/model.safetensorsOther494.4 MBff0045444eca
checkpoints/llama-124m/runs/run_040/model.safetensorsOther494.4 MB39f7710f8057
checkpoints/llama-124m/runs/run_041/model.safetensorsOther494.4 MBdec8a2a7cc02
checkpoints/llama-124m/runs/run_042/model.safetensorsOther494.4 MB81e357f7cc9e
checkpoints/llama-124m/runs/run_043/model.safetensorsOther494.4 MBb84e4ca34db4
checkpoints/llama-124m/runs/run_044/model.safetensorsOther494.4 MBbd2e4ea4ffa3
checkpoints/llama-124m/runs/run_045/model.safetensorsOther494.4 MB4919b6a1bd45
checkpoints/llama-124m/runs/run_046/model.safetensorsOther494.4 MBb13269336ac7
checkpoints/llama-124m/runs/run_047/model.safetensorsOther494.4 MBf802abfba222
checkpoints/llama-124m/runs/run_048/model.safetensorsOther494.4 MB6077bb464315
checkpoints/llama-124m/runs/run_049/model.safetensorsOther494.4 MB3231af99e392
checkpoints/llama-124m/runs/run_050/model.safetensorsOther494.4 MBaaeb1981ccb8
checkpoints/llama-124m/runs/run_051/model.safetensorsOther494.4 MB3f2a303d47d3
checkpoints/llama-124m/runs/run_052/model.safetensorsOther494.4 MBdae870c5e137
checkpoints/llama-124m/runs/run_053/model.safetensorsOther494.4 MBc4ea1f9965f3
checkpoints/llama-124m/runs/run_054/model.safetensorsOther494.4 MB05597ed2a489
checkpoints/llama-124m/runs/run_055/model.safetensorsOther494.4 MBac309616326a
checkpoints/llama-124m/runs/run_056/model.safetensorsOther494.4 MBe5f167af1dcd
checkpoints/llama-124m/runs/run_057/model.safetensorsOther494.4 MBcd6b9bb16ada
checkpoints/llama-124m/runs/run_058/model.safetensorsOther494.4 MB9afef3f1f7be
checkpoints/llama-124m/runs/run_059/model.safetensorsOther494.4 MB010aaf737cd3
checkpoints/llama-124m/runs/run_060/model.safetensorsOther494.4 MBdac65a6a6a6c
checkpoints/llama-124m/runs/run_061/model.safetensorsOther494.4 MBfa10a3a77b87
checkpoints/llama-124m/runs/run_062/model.safetensorsOther494.4 MB2a12013cd70e
checkpoints/llama-124m/runs/run_063/model.safetensorsOther494.4 MBfaede7ce5ddb
checkpoints/llama-124m/runs/run_064/model.safetensorsOther494.4 MB3161cd3b3a23
checkpoints/llama-124m/runs/run_065/model.safetensorsOther494.4 MBcb6104487c2c
checkpoints/llama-124m/runs/run_066/model.safetensorsOther494.4 MBa39f16ca69f6
checkpoints/llama-124m/runs/run_067/model.safetensorsOther494.4 MB3b16a8ac5c26
checkpoints/llama-124m/runs/run_068/model.safetensorsOther494.4 MBd2080096bed9
checkpoints/llama-124m/runs/run_069/model.safetensorsOther494.4 MBb68be3248cfa
checkpoints/llama-124m/runs/run_070/model.safetensorsOther494.4 MBd9903330d304
checkpoints/llama-124m/runs/run_071/model.safetensorsOther494.4 MBc24d3ce02460
checkpoints/llama-124m/runs/run_072/model.safetensorsOther494.4 MB707e15db525d
checkpoints/llama-124m/runs/run_073/model.safetensorsOther494.4 MBf04b8f7fb569
checkpoints/llama-124m/runs/run_074/model.safetensorsOther494.4 MBf04b8f7fb569
checkpoints/llama-124m/runs/run_075/model.safetensorsOther494.4 MBf04b8f7fb569
checkpoints/llama-124m/runs/run_076/model.safetensorsOther494.4 MBf04b8f7fb569
checkpoints/llama-124m/runs/run_077/model.safetensorsOther494.4 MBf04b8f7fb569
checkpoints/llama-124m/runs/run_078/model.safetensorsOther494.4 MBf04b8f7fb569
checkpoints/llama-124m/runs/run_079/model.safetensorsOther494.4 MBf04ff511a02c
checkpoints/llama-124m/runs/run_080/model.safetensorsOther494.4 MBf04ff511a02c
checkpoints/llama-124m/runs/run_081/model.safetensorsOther494.4 MBdb78a146fcbc
checkpoints/llama-124m/runs/run_082/model.safetensorsOther494.4 MBdef821ed9bcb
checkpoints/llama-124m/runs/run_083/model.safetensorsOther494.4 MBdb78a146fcbc
checkpoints/llama-124m/runs/run_084/model.safetensorsOther494.4 MBdb78a146fcbc
checkpoints/llama-124m/runs/run_085/model.safetensorsOther494.4 MBdef821ed9bcb
checkpoints/llama-124m/runs/run_086/model.safetensorsOther494.4 MBdb78a146fcbc
checkpoints/llama-124m/runs/run_087/model.safetensorsOther494.4 MB79ac25270195
checkpoints/llama-124m/runs/run_088/model.safetensorsOther494.4 MB298a21256e2e
checkpoints/llama-124m/runs/run_089/model.safetensorsOther494.4 MB8f386ffe1d30
checkpoints/llama-124m/runs/run_090/model.safetensorsOther494.4 MBc7b6c55eeb2d
checkpoints/llama-124m/runs/run_091/model.safetensorsOther494.4 MB113836e8a6c8
checkpoints/llama-124m/runs/run_092/model.safetensorsOther494.4 MBca53033626d6
checkpoints/llama-124m/runs/run_093/model.safetensorsOther494.4 MBf299359911fa
checkpoints/llama-124m/runs/run_094/model.safetensorsOther494.4 MB48e028063440
checkpoints/llama-124m/runs/run_095/model.safetensorsOther494.4 MB8932e2f0d8d8
checkpoints/llama-124m/runs/run_096/model.safetensorsOther494.4 MBd9da96444b73
checkpoints/llama-124m/runs/run_097/model.safetensorsOther494.4 MB65cacd8c5cd6
checkpoints/llama-124m/runs/run_098/model.safetensorsOther494.4 MB9d202eeb9b81
checkpoints/llama-124m/runs/run_099/model.safetensorsOther494.4 MB2643788f9d31
checkpoints/llama-124m/runs/run_100/model.safetensorsOther494.4 MB67f9b1f1cb17
checkpoints/llama-124m/runs/run_101/model.safetensorsOther494.4 MBa3bb5ee3ab69
checkpoints/llama-124m/runs/run_102/model.safetensorsOther494.4 MBb0b67d52faeb
checkpoints/llama-124m/runs/run_103/model.safetensorsOther494.4 MBc4dbc53072b0
checkpoints/llama-124m/runs/run_104/model.safetensorsOther494.4 MBb1ce384b11c1
checkpoints/llama-124m/runs/run_105/model.safetensorsOther494.4 MB07c8e62ad6d6
checkpoints/llama-124m/runs/run_106/model.safetensorsOther494.4 MB79a3004a6ce9
checkpoints/llama-124m/runs/run_107/model.safetensorsOther494.4 MBfa1fb09df762
checkpoints/llama-124m/runs/run_108/model.safetensorsOther494.4 MB7e994fe3b6e8
checkpoints/llama-124m/runs/run_109/model.safetensorsOther494.4 MB85d567bdda19
checkpoints/llama-124m/runs/run_110/model.safetensorsOther494.4 MB8a16471eeab2
checkpoints/llama-124m/runs/run_111/model.safetensorsOther494.4 MB371321212c52
tokens/gpt-neox/streams/stream_001.binOther298.8 MBd998427c0b87
tokens/gpt-neox/streams/stream_002.binOther298.8 MB23418a8fb480
tokens/gpt-neox/streams/stream_003.binOther298.8 MB36e25ec2fa7a
tokens/gpt-neox/streams/stream_004.binOther298.8 MBfc0df7d50454
tokens/gpt2/cosmopedia.binOther3.4 GB09e11ab3a492
tokens/gpt2/fineweb_2019-2021.binOther5.3 GB8842f46ebdfe
tokens/gpt2/streams/stream_001.binOther349.6 MB86f0e8b597aa
tokens/gpt2/streams/stream_002.binOther349.6 MB350d8aec26ac
tokens/gpt2/streams/stream_003.binOther349.6 MBe5c2ce1a2171
tokens/gpt2/streams/stream_004.binOther349.6 MB3266b04a3cb7
tokens/gpt2/streams/stream_005.binOther199.8 MBaf3a1ceb0d54
tokens/gpt2/streams/stream_006.binOther199.8 MB56683de3d128
tokens/gpt2/streams/stream_007.binOther299.6 MBb8cc746708c4
tokens/gpt2/streams/stream_008.binOther299.6 MB05fa9eb7e76e
tokens/gpt2/streams/stream_009.binOther299.6 MBbfa5e11a2118
tokens/gpt2/streams/stream_010.binOther299.6 MB223463f03843
tokens/gpt2/streams/stream_011.binOther199.8 MB2ea0e9aa5796
tokens/gpt2/streams/stream_012.binOther199.8 MBa5cd0cb4109c
tokens/gpt2/streams/stream_013.binOther199.8 MB9197d3d99784
tokens/gpt2/streams/stream_014.binOther199.8 MBf7285e641c96
tokens/gpt2/streams/stream_015.binOther299.6 MB219b905014b9
tokens/gpt2/streams/stream_016.binOther299.6 MB29ccae3edd40
tokens/gpt2/streams/stream_017.binOther299.6 MB52fd2b2f0fbb
tokens/gpt2/streams/stream_018.binOther299.6 MB1d76a1b0560b
tokens/gpt2/streams/stream_019.binOther299.6 MB219b905014b9
tokens/gpt2/streams/stream_020.binOther359.6 MBc5f373fad583
tokens/gpt2/streams/stream_021.binOther359.6 MB43227383ac89
tokens/gpt2/streams/stream_022.binOther359.6 MB22d78a25599a
tokens/gpt2/streams/stream_023.binOther359.6 MB1487822fa66d
tokens/gpt2/streams/stream_024.binOther339.6 MB99bed5b4aef8
tokens/gpt2/streams/stream_025.binOther339.6 MB45887aafada5
tokens/gpt2/streams/stream_026.binOther339.6 MBf4daa474b1f6
tokens/gpt2/streams/stream_027.binOther339.6 MB38caf2085378
.gitattributesRepository2.5 KB—

License and Download

License
odc-by
Access
No access gate
Download from Liangzhi Li

Released by Liangzhi Li through its official repository on Hugging Face.