sora/evalstone
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8 Commits 1 Branch 0 Tags
Commit Graph

8 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
sora
1308ddd251 feat(run.py): add --thinking-max-tokens-scale and official suite 
- Add --thinking-max-tokens-scale to multiply max_tokens when
  --thinking is enabled.
- Add 'official' suite covering all benchmarks in the public
  comparison tables (Kimi/GLM/DS etc).
- Print scale factor in run summary when thinking is on.
 2026-07-23 02:57:53 +00:00
sora
a3251f056f feat(run.py): default generation config for unknown benchmarks 
If a benchmark is not present in the YAML config, use default
parameters instead of skipping:
- temperature: 0.0
- top_p: 1.0
- stream: true
- max_tokens: 32768
 2026-07-23 02:40:32 +00:00
sora
3afd57b5a4 feat(pull_swe_bench_images): support comma-separated --dataset 
- Allow --dataset swe_bench_verified,swe_bench_lite to pre-pull
  multiple SWE-bench variants in one run.
- Validate dataset keys before loading.
- Update myread.md with multi-dataset example.
 2026-07-23 02:34:49 +00:00
sora
2ee0af0728 docs: add resource prep section and sync docker/bash helpers 
- Rewrite myread.md with proper markdown and four download sources:
  code, data, evalscope-complete-py312 image, execution images.
- Add bash/collect_results.py, perf_backup.py, pull_swe_bench_images.py
  for result aggregation, breakpoint perf recovery, and SWE-bench
  image pre-pulling.
- Update bash/run.py with multi-run suites, perf backup/restore, and
  whitelist-based summary.
- Update config/dpv4-int8_nothinking.yaml benchmark parameters.
- Ignore /docker_images and /results in .gitignore.
 2026-07-23 02:18:15 +00:00
sora
03b49a39d0 all 2026-07-22 03:26:58 +00:00
sora
cfa58f869f all 2026-07-21 09:32:49 +00:00
aaxiyao
85e1a9796d xii 2026-07-10 04:02:28 +00:00
sora
d7547f642a readme：如下 2026-07-08 08:57:50 +00:00