Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
BonanDing
/
worldmem-baseline-evals
Like
0
evaluation
minecraft
realestate10k
world-model
License:
mixed-upstream-licenses
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
worldmem-baseline-evals
/
deployment
163 kB
Ctrl+K
Ctrl+K
1 contributor
History:
16 commits
BonanDing
Add constrained DecMem STM6/topk27 Minecraft evaluation
aa4688c
verified
24 days ago
manifests
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago
cache_metrics.py
561 Bytes
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago
cluster_metadata.json
5.72 kB
Run GPU evaluations directly from prepared environment interpreters
25 days ago
context_budget_audit.json
26.5 kB
Add strictly past-only Geometry Forcing context and guidance diagnostics
24 days ago
diagnose_matrix_game2.py
6.87 kB
Add five separate Berzelius Matrix-Game diagnostic tasks
24 days ago
diagnose_matrix_game2_1h200.sh
1.61 kB
Add five separate Berzelius Matrix-Game diagnostic tasks
24 days ago
download_assets.py
1.65 kB
Pin inspected model assets and record portable deployment provenance
25 days ago
evaluate_decmem_8h200.sh
2.28 kB
Run GPU evaluations directly from prepared environment interpreters
25 days ago
evaluate_decmem_budget_8h200.sh
3.38 kB
Add constrained DecMem STM6/topk27 Minecraft evaluation
24 days ago
evaluate_geometry_forcing_8h200.sh
2.96 kB
Run full causal Geometry Forcing RE10K evaluation at 12 slots and CFG1
24 days ago
evaluate_live_8h200.sh
3.13 kB
Match LIVE to 12 frame slots and gate full evaluation with target GPU preflight
24 days ago
evaluate_matrix_game2_8h200.sh
2.34 kB
Run GPU evaluations directly from prepared environment interpreters
25 days ago
geometry_causal_controls.py
7.56 kB
Run full causal Geometry Forcing RE10K evaluation at 12 slots and CFG1
24 days ago
geometry_causal_controls_1h200.sh
1.66 kB
Add strictly past-only Geometry Forcing context and guidance diagnostics
24 days ago
geometry_forcing_constraints.txt
3.32 kB
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago
matrix_native_controls.py
6.84 kB
Add exact Matrix official demo and native-image action controls
24 days ago
matrix_native_controls_1h200.sh
1.9 kB
Add exact Matrix official demo and native-image action controls
24 days ago
portability_audit.json
15.9 kB
Declare VSA pytest dependency and add focused DecMem CPU repair job
25 days ago
repair_decmem_environment_berzelius.sh
1.26 kB
Declare VSA pytest dependency and add focused DecMem CPU repair job
25 days ago
requirements_decmem.txt
523 Bytes
Declare VSA pytest dependency and add focused DecMem CPU repair job
25 days ago
requirements_geometry_forcing.txt
658 Bytes
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago
requirements_matrix_game2.txt
362 Bytes
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago
setup_environment_berzelius.sh
4.41 kB
Use required project cache for TMPDIR and TRITON_CACHE_DIR in all jobs
25 days ago
smoke_decmem_1h200.sh
2.28 kB
Run GPU evaluations directly from prepared environment interpreters
25 days ago
smoke_geometry_forcing_1h200.sh
2.37 kB
Use native Geometry Forcing keyframes and interpolation on the common reverse loop
24 days ago
smoke_live_1h200.sh
2.3 kB
Run GPU evaluations directly from prepared environment interpreters
25 days ago
smoke_matrix_game2_1h200.sh
2.32 kB
Run GPU evaluations directly from prepared environment interpreters
25 days ago
verify_data.py
2.38 kB
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago
verify_node.py
882 Bytes
Add isolated Minecraft and RE10K baseline evaluation suite
25 days ago