Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Lgr54HFi
/
chomera
like
0
chimera51
custom_code
arxiv:
12 papers
Model card
Files
Files and versions
xet
Community
main
chomera
309 kB
Ctrl+K
Ctrl+K
1 contributor
History:
45 commits
Lgr54HFi
fix: MoE intermediate_size not scaled for tiny — 158M→4M MoE params
6cb7b4d
verified
9 days ago
chimera
fix: MoE intermediate_size not scaled for tiny — 158M→4M MoE params
9 days ago
tests
Upload folder using huggingface_hub
10 days ago
.gitattributes
Safe
1.52 kB
initial commit
10 days ago
.gitignore
Safe
230 Bytes
Upload folder using huggingface_hub
10 days ago
README.md
Safe
9.11 kB
Upload folder using huggingface_hub
10 days ago
chimera_turbo.py
Safe
22.5 kB
perf: tune chimera_turbo.py for 300-step convergence + throughput
9 days ago
config.json
Safe
25.5 kB
Upload folder using huggingface_hub
10 days ago
gguf_import.py
Safe
29.1 kB
Upload folder using huggingface_hub
10 days ago
inference.py
Safe
12.3 kB
Upload folder using huggingface_hub
10 days ago
launch_turbo.sh
Safe
3.06 kB
fix: tcmalloc debug .so crash, add error trapping, chmod note
9 days ago
pyproject.toml
Safe
789 Bytes
Upload folder using huggingface_hub
10 days ago
train.py
Safe
9.22 kB
Upload folder using huggingface_hub
10 days ago
train_fast.py
Safe
4.96 kB
Upload folder using huggingface_hub
10 days ago
train_hyper.py
7.57 kB
fix: batch_size 32→4 base (GrowLength scales up, _safe_batch caps)
9 days ago
