494 kB

Ctrl+K

1 contributor

History: 2 commits

goldenfox

Final bench: add thinking-at-512-budget condition (2/10 vs ledger 6/10)

0625b14 verified 10 days ago

bench_ledger_needle.py

31.9 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
ledger-needle-compare.html

10.6 kB
Final bench: add thinking-at-512-budget condition (2/10 vs ledger 6/10) 10 days ago
ledger-needle-ours.html

125 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-ledger-ours.jsonl

118 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-qwen25-05b-full.jsonl

28 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-qwen25-15b-full.jsonl

22.5 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-qwen3-06b-nothink-budget512.jsonl

26.9 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-qwen3-06b-nothink-full.jsonl

25.9 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-qwen3-06b-thinking-budget512.jsonl

30.1 kB
Final bench: add thinking-at-512-budget condition (2/10 vs ledger 6/10) 10 days ago
results-qwen3-06b-thinking-full.jsonl

28.2 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-smollm2-360m-full.jsonl

20.5 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago
results-tinyllama-11b-full.jsonl

26.1 kB
Marimo Diffusion 0.6B: checkpoint, sampler, OpenAI server, ledger-needle bench 10 days ago