florin-parser-nano / .eval_results /parsebench.yaml
ammoman21's picture
Fix .eval_results/parsebench.yaml: standard HF eval-result array schema
7660bd0 verified
Raw
History Blame Contribute Delete
2.2 kB
- dataset:
id: llamaindex/ParseBench
task_id: mean
value: 76.92
date: '2026-08-18'
source:
url: https://huggingface.co/datasets/llamaindex/ParseBench
name: ParseBench
user: florin-inc
notes: "Pipeline name: florin_parser_nano (provider subclass, run-llama/ParseBench PR #99). Mean of two independent full-corpus runs (76.95, 76.89, delta 0.06), all 2,079 files, five dimensions. LoRA fine-tune of KDLAI/KDL-Frontier-Parser-nano (language layers only) plus markdown-emission patches; production prompt unchanged. Chart LLM normaliser off (LLAMACLOUD_BENCH_LLM_NORMALIZATION=off). Same-environment baseline reproduction of kdl_frontier_nano: 72.65. Reproduction repo: https://github.com/ammoman21/parsebench-open-weight-sota"
- dataset:
id: llamaindex/ParseBench
task_id: table
value: 86.10
date: '2026-08-18'
source:
url: https://huggingface.co/datasets/llamaindex/ParseBench
name: ParseBench
user: florin-inc
notes: "Pipeline name: florin_parser_nano (run-llama/ParseBench PR #99)"
- dataset:
id: llamaindex/ParseBench
task_id: chart
value: 65.33
date: '2026-08-18'
source:
url: https://huggingface.co/datasets/llamaindex/ParseBench
name: ParseBench
user: florin-inc
notes: "Pipeline name: florin_parser_nano (run-llama/ParseBench PR #99)"
- dataset:
id: llamaindex/ParseBench
task_id: text_content
value: 87.34
date: '2026-08-18'
source:
url: https://huggingface.co/datasets/llamaindex/ParseBench
name: ParseBench
user: florin-inc
notes: "Pipeline name: florin_parser_nano (run-llama/ParseBench PR #99)"
- dataset:
id: llamaindex/ParseBench
task_id: text_formatting
value: 71.69
date: '2026-08-18'
source:
url: https://huggingface.co/datasets/llamaindex/ParseBench
name: ParseBench
user: florin-inc
notes: "Pipeline name: florin_parser_nano (run-llama/ParseBench PR #99)"
- dataset:
id: llamaindex/ParseBench
task_id: layout
value: 74.15
date: '2026-08-18'
source:
url: https://huggingface.co/datasets/llamaindex/ParseBench
name: ParseBench
user: florin-inc
notes: "Pipeline name: florin_parser_nano (run-llama/ParseBench PR #99)"