ViuAI
/

ViuMini-Dense-360M

Text Generation

Model card Files Files and versions

ViuMini-Dense-360M

2.27 GB

Ctrl+K

Ctrl+K

2 contributors

History: 330 commits

ViuAI's picture

feat: update RTX 5090 runner and config

9f69669 verified 2 days ago

data
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
docs
feat: update RTX 5090 runner and config 2 days ago
logs
sync log step_1000 3 days ago
model
feat: update RTX 5090 notebook runner and optimized config 2 days ago
scratch
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
tokenizer
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
.gitattributes

290 Bytes
Fix CUDA OOM on T4: cast model to amp_dtype directly, batch_size=2, safe RMSNorm 5 days ago
.gitignore

177 Bytes
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
NOTES.md

43.1 kB
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
README.md

6.75 kB
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
RUN_ON_CLOUD.ipynb

11 kB
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
basic_arithmetic_bodmas_tables.parquet

678 kB
xet

docs & scripts: add full-scale 5-domain milestone (145.93GB/105B tokens) 16 days ago
requirements.txt

317 Bytes
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening 4 days ago
run_notebook_rtx5090.py

4.15 kB
feat: update RTX 5090 runner and config 2 days ago