Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
tangledgroup
/
tangled-alpha-0.8-core
like
0
Follow
TangledGroup
5
Text Generation
Transformers
20 datasets
107 languages
llama
chat
core
base
instruct
reason
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
tangled-alpha-0.8-core
/
scripts
Ctrl+K
Ctrl+K
2 contributors
History:
5 commits
mtasic85
global_batch_size: 512; micro_batch_size: 2; class_path: grokadamw.GrokAdamW
dee3ffa
about 2 months ago
backup
pretrain
about 2 months ago
core_base_datasets.py
Safe
3.81 kB
pretrain
about 2 months ago
core_instruct_datasets.py
Safe
2.13 kB
pretrain
about 2 months ago
prepare_core_datasets.py
2.1 kB
pretrain
about 2 months ago
pretrain_core_model.yaml
Safe
5.35 kB
global_batch_size: 512; micro_batch_size: 2; class_path: grokadamw.GrokAdamW
about 2 months ago
requirements.in
Safe
437 Bytes
global_batch_size: 512; micro_batch_size: 2; class_path: grokadamw.GrokAdamW
about 2 months ago
train_tokenizer.py
2.62 kB
pretrain
about 2 months ago
utils.py
Safe
5.34 kB
pretrain
about 2 months ago
