18.6 GB

Ctrl+K

4 contributors

History: 20 commits

hkust-aaron

Use BF16 state at every CUDA batch and stabilize physical-ring attention

623a14e verified 4 days ago

assets
Update report, runtime profiles and Chinese documentation 5 days ago
docs
Use BF16 state at every CUDA batch and stabilize physical-ring attention 4 days ago
evaluation_data
Name evaluation resources explicitly 14 days ago
runtime
Use BF16 state at every CUDA batch and stabilize physical-ring attention 4 days ago
sglang_models
Use BF16 inference and align figures and results with the technical report 6 days ago
vision
Release YANchor-4B 15 days ago
wheels
Release YANchor-4B 15 days ago
.dockerignore
114 Bytes
Use BF16 inference and align figures and results with the technical report 6 days ago
.gitattributes
1.22 kB
Update report, runtime profiles and Chinese documentation 5 days ago
.gitignore
77 Bytes
Use BF16 inference and align figures and results with the technical report 6 days ago
CITATION.cff
1.03 kB
Align EdgeRock model card, figures and report with the current paper 6 days ago
Dockerfile
413 Bytes
Use BF16 inference and align figures and results with the technical report 6 days ago
LICENSE
18 kB
Align EdgeRock model card, figures and report with the current paper 6 days ago
LICENSE-CODE
11.4 kB
Align EdgeRock model card, figures and report with the current paper 6 days ago
NOTICE
3.61 kB
Align EdgeRock model card, figures and report with the current paper 6 days ago
README.md
35.2 kB
Use platform URLs for bilingual documentation navigation 5 days ago
README_zh-CN.md
34.9 kB
Fix Chinese README emphasis rendering 5 days ago
USAGE.md
11.1 kB
Update report, runtime profiles and Chinese documentation 5 days ago
config.json
2.62 kB
Use BF16 inference and align figures and results with the technical report 6 days ago
configuration_edgerock.py
945 Bytes
Use BF16 inference and align figures and results with the technical report 6 days ago
generation_config.json
120 Bytes
Release YANchor-4B 15 days ago
llms.txt
2.46 kB
Update report, runtime profiles and Chinese documentation 5 days ago
model-00001-of-00003.safetensors
3.99 GB
xet

Release YANchor-4B 15 days ago
model-00002-of-00003.safetensors
3.97 GB
xet

Release YANchor-4B 15 days ago
model-00003-of-00003.safetensors
1.2 GB
xet

Release YANchor-4B 15 days ago
model.safetensors.index.json
45.5 kB
Release YANchor-4B 15 days ago
modeling_edgerock.py
67.9 kB
Use BF16 state at every CUDA batch and stabilize physical-ring attention 4 days ago
pyproject.toml
1.34 kB
Use BF16 inference and align figures and results with the technical report 6 days ago
requirements.txt
572 Bytes
Release YANchor-4B 15 days ago
run.py
14.8 kB
Use BF16 inference and align figures and results with the technical report 6 days ago
tokenizer.json
20 MB
xet

Release YANchor-4B 15 days ago
tokenizer_config.json
1.12 kB
Release YANchor-4B 15 days ago
vllm_edgerock.py
7.89 kB
Use BF16 inference and align figures and results with the technical report 6 days ago