Commit History

chore (deployment): Add HuggingFace spaces configuration yaml.
b2d79c4
Running

kpfadnis commited on

chore (build): Updating security policy for Huggingface spaces.
a93281f

kpfadnis commited on

chore (build): Updating security policy for Huggingface spaces.
62aaec2

kpfadnis commited on

chore (build): Updating security policy for Huggingface spaces.
61c81bd

kpfadnis commited on

feat (converters): align AgentIF, ComplexBench, IFEval with public runner output layouts
2e5b318

kpfadnis commited on

refactor: type consolidation, chat component promotion, generation UX fixes, converter cleanup
753fcc5

kpfadnis commited on

feat (complexbench): add ComplexBench converter
2652ebb

kpfadnis commited on

feat (ifeval): add IFEval converter and program trace event support
a55b84f

kpfadnis commited on

feat: add ModelCharacteristics view and fix BFCL converter data quality
2542139

kpfadnis commited on

fix (bfcl): clarify run directory layout and model-dir vs model-id distinction in README
5ad9dc7

kpfadnis commited on

fix (expression-builder): reject empty expressions and fix null vs undefined invalid state
c1e232d

kpfadnis commited on

feat (tau2bench): add tau2bench converter, README, and update converters index
2d713d7

kpfadnis commited on

fix: lint and build errors ahead of merge to main
6352dc8

kpfadnis commited on

feat (acebench): ACEBench converter, README, and architecture docs
b359fde

kpfadnis commited on

feat: agentic task type, BFCL multi-turn converter, status badges, and ranking fix
d8e2332

kpfadnis commited on

feat: schema v2, tool_calling evaluation, BFCL converter, UI polish, and expression fixes (#18)
95131e1
unverified

kpfadnis commited on

fix (validator): Fix input file validator for 'chat' task.
bde7974

kpfadnis commited on

chore (build): Upgrade NextJS version to fix security vulnerability
b9bcfa6

kpfadnis commited on

feat (chat task): Minor enhancements to chat task view.
3939dda

kpfadnis commited on

Merge pull request #15 from IBM/feat_chat_template_support
d639f28
unverified

kpfadnis commited on

chore (maintainance): Update depdencies, copyright and minimal support for chat template.
e23b66d

kpfadnis commited on

Merge pull request #14 from jwm4/patch-1
f0a28d2
unverified

kpfadnis commited on

Fix typo in README build instructions
18a5d8c

bmurdock commited on

fix (aggregator): Fix sort in median aggregator.
275e85f

kpfadnis commited on

fix (metrics): Fix median aggregator due to incorrect sort.
4d12df4

kpfadnis commited on

fix (build): Fix broken build due to typescript error.
b0476f6

kpfadnis commited on

chore (build): Upgrade dependencies.
4c91116

kpfadnis commited on

chore (build): Upgrade depedencies.
500812d

kpfadnis commited on

fix (CSS): Minor CSS fix for performance overview tab.
5b28369

kpfadnis commited on

fix (performance overview): Use normalized scores for radar plots.
a66466f

kpfadnis commited on

feat (Filters): Allow user to select all values in a filter.
1cd25a0

kpfadnis commited on

fix (CSS): Minor CSS fixes for performance view.
825c201

kpfadnis commited on

fix (aggregators): Minor fix to median aggregator.
ba53458

kpfadnis commited on

feat (aggregator): Added support for median aggregator.
5db7074

kpfadnis commited on

feat (filters): Enable filtering on model & metric comparison views.
988e116

kpfadnis commited on

chore (UX): Create dedicated worker to handle filtering in model behavior view.
329f495

kpfadnis commited on

fix (model behavior): Fix crash in model behavior due to unrefreshed state.
53257e4

kpfadnis commited on

feat (expression): Experimental support for expression based filtering in model behavior. (#13)
ae7d3b8
unverified

kpfadnis commited on

feat (metric behavior): Allow user to drill down in metric behavior view. (#12)
bac04f0

kpfadnis commited on

feat (model comparator): Enhanced control and added interactablity to single metric plot (#11)
8bab137

kpfadnis commited on

fix (onboard): CSS fix to handle overflow during on-boarding process.
0a1d0ea

kpfadnis commited on

fix (RAG): Crash due to missing context in RAG.
3dffb90

kpfadnis commited on

Prevent accidental back button click in visualize page (#10)
a810633

captiancoder commited on

chore (build): Bump version.
5b74493

kpfadnis commited on

feat (comments): Allow user to delete and edit comment.
b6e592e

kpfadnis commited on

fix (export): Minor fix to export with additional notebook to merge.
4594d15

kpfadnis commited on

chore (data): Added additional example data.
d769391

kpfadnis commited on

feat: Add Ragas integration notebook (#9)
bcb2553

Yannis Katsis commited on

chore: Bump version.
6c9e7f7

kpfadnis commited on

chore: update README with experiment results file format (#7)
22294bc

Siva Sankalp commited on