Spaces:
Running
Running
Commit History
21 days ago
-
Visualize: starter questions carry their plans (no planning call), hedged model calls so one slow provider can't stall a chart, sturdier label discovery, spread samples, whole-number histograms
Verified signature859a42c -
Visualize: ask a dataset a question, get an exact chart with the rows behind every mark (small datasets first: instant glance charts, batched model labels, drill-down, scoped follow-ups)
Verified signature917845f
23 days ago
-
0.2.2: route through the authenticated optillm proxy (fast tier via DI_MIN_MAX_TOKENS), prompt fixes (plain prose, no invented specifics, no callbacks/placeholders), two-order accuracy-first preference judge, accurate dataset-card provenance
Verified signaturebf2993f -
0.2.1: give reasoning models (gpt-oss) token headroom + low reasoning effort, so grading, preference ranking and ping aren't cut off; wheel rebuilt
Verified signature7e4e57b -
Default engine: openai/gpt-oss-20b via DeepInfra (more concrete answers, ~2x faster than Llama-3.1-8B in a 5-row test)
Verified signature2803801 -
Default engine: meta-llama/Llama-3.1-8B-Instruct via DeepInfra on HF Inference Providers (was Qwen3-4B on nscale)
Verified signature13bb7cb
25 days ago
-
Curate a corpus: clean, calibrate, create, compose on a sample, plus a recipe and runner for your own machines
Verified signature4f740eb