STEP35 Burn Agent 90949efa11 bench: add Falcon-H1-Tiny-90M tool calling benchmark (closes #103) ...

- benchmarks/falcon-h1-tiny-90m.md: 123-line benchmark doc
- Covers model specs, 4 test categories (schema parsing, JSON validity,
  multi-tool, CPU latency), expected results, use cases, limitations
- Documents 90M param model for edge deployment (45MB FP16, ~23MB Q4)

2026-04-26 09:07:09 -04:00

..

falcon-h1-tiny-90m.md

bench: add Falcon-H1-Tiny-90M tool calling benchmark (closes #103)

2026-04-26 09:07:09 -04:00

perplexity_results.json

feat: wikitext-2 corpus + perplexity benchmark script (closes #21)

2026-04-12 00:39:14 -04:00

prompts.json

feat: add standardized benchmarking prompts

2026-03-30 21:14:48 +00:00

run_benchmarks.py

feat: multi-backend benchmark suite with TTFT + memory tracking (#37)

2026-04-13 14:05:17 +00:00

run_long_session.py

burn: add long-session quality test (Issue #12) (#39)

2026-04-13 19:59:22 +00:00

run_perplexity.py

feat: wikitext-2 corpus + perplexity benchmark script (closes #21)

2026-04-12 00:39:14 -04:00

test_prompts.json

Add benchmark test prompts for quality comparison (Issue #22)

2026-03-31 17:31:05 +00:00