Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
Log In
Sign Up

Vjeong
/

LLM-1B-Lab

Model card Files Files and versions

LLM-1B-Lab / llm_lab

226 kB

Ctrl+K

Ctrl+K

2 contributors

History: 35 commits

Vjeong's picture

Fix dead split parameter in PackedStreamingDataset._load_dataset

0cd5689 about 21 hours ago

config
Fix LR warmup ordering and align adam_eps with Meta LLaMA 6 days ago
data
Fix dead split parameter in PackedStreamingDataset._load_dataset about 21 hours ago
evaluation
Fix gradient clipping thresholds in dynamics and checklist modules 11 days ago
model
Fix dtype mismatch in RoPE cos/sin for mixed precision training 4 days ago
training
Refactor runner.py: extract shared setup logic into _setup_and_train helper 4 days ago
utils
fix(device): correct attribute name from total_mem to total_memory 29 days ago
__init__.py

1.36 kB
Add Code CPT pipeline for injecting Python code capability 7 days ago