9.11 GB

Ctrl+K

1 contributor

History: 9 commits

Goddragon

Sync latest vllm-fast, enable position pooling by default, document prefix/head cache usage

8fd2056 verified 2 days ago

.eval_results
Remove dataset revision pins from Typed Decisions eval results 5 days ago
backbone
Publish model and typed-decisions evaluation 7 days ago
evaluation
Sync latest vllm-fast, enable position pooling by default, document prefix/head cache usage 2 days ago
evaluation_tools
Publish model and typed-decisions evaluation 7 days ago
provenance
Publish model and typed-decisions evaluation 7 days ago
tokenizer
Publish model and typed-decisions evaluation 7 days ago
vllm-fast
Sync latest vllm-fast, enable position pooling by default, document prefix/head cache usage 2 days ago
.gitattributes

1.58 kB
Publish model and typed-decisions evaluation 7 days ago
LICENSE

11.8 kB
Publish model and typed-decisions evaluation 7 days ago
NOTICE.md

293 Bytes
Publish model and typed-decisions evaluation 7 days ago
README.md

7.61 kB
Sync latest vllm-fast, enable position pooling by default, document prefix/head cache usage 2 days ago
SHA256SUMS

4.67 kB
Sync latest vllm-fast, enable position pooling by default, document prefix/head cache usage 2 days ago
calibration.json

2.01 kB
Fix release metadata and evaluation wrapper: add SHA256SUMS/calibration.json, remove unsupported --fail-fast, correct run_metadata claims 2 days ago
model_manifest.json

4.1 kB
Publish model and typed-decisions evaluation 7 days ago
pointer_head.safetensors

5.25 MB
xet

Publish model and typed-decisions evaluation 7 days ago
run_evaluation.py

8.31 kB
Sync latest vllm-fast, enable position pooling by default, document prefix/head cache usage 2 days ago