Text Classification
PEFT
Safetensors
strands-decider
decision-model
hobson
lora
qwen3.5
classification
calibration
typed-decisions
Eval Results (legacy)
Instructions to use StrandsAgents/strands-decider-2B-hobson-v21 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use StrandsAgents/strands-decider-2B-hobson-v21 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download eval/summary.json from StrandsAgents/strands-decider-2B-hobson-v21: direct link, hf CLI and curl.
- Browser
- Download file 3.47 kB
-
https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v21/resolve/main/eval/summary.json
- Command line
-
hf download hf://StrandsAgents/strands-decider-2B-hobson-v21/eval/summary.json
-
curl -L -o summary.json https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v21/resolve/main/eval/summary.json
3.47 kB
| { | |
| "internal": { | |
| "eval: [2] gen:all_conditions": { | |
| "accuracy": 0.824, | |
| "n": 34 | |
| }, | |
| "eval: [2] gen:dates": { | |
| "accuracy": 0.871, | |
| "n": 31 | |
| }, | |
| "eval: [2] gen:exception": { | |
| "accuracy": 0.946, | |
| "n": 37 | |
| }, | |
| "eval: [2] gen:lookup_chain": { | |
| "accuracy": 0.8, | |
| "n": 40 | |
| }, | |
| "eval: [2] gen:numbers": { | |
| "accuracy": 0.848, | |
| "n": 33 | |
| }, | |
| "eval: [2] gen:precedence": { | |
| "accuracy": 0.917, | |
| "n": 36 | |
| }, | |
| "eval: [2] gen:rubric": { | |
| "accuracy": 0.794, | |
| "n": 34 | |
| }, | |
| "eval: [2] gen:surface_trap": { | |
| "accuracy": 0.958, | |
| "n": 48 | |
| }, | |
| "eval: [2] gen:tradeoff": { | |
| "accuracy": 0.7, | |
| "n": 40 | |
| }, | |
| "eval: [2] gen:underdetermined": { | |
| "accuracy": 0.765, | |
| "n": 17 | |
| }, | |
| "eval: [3] gen:all_conditions": { | |
| "accuracy": 0.889, | |
| "n": 9 | |
| }, | |
| "eval: [3] gen:borderline_rubric": { | |
| "accuracy": 0.538, | |
| "n": 13 | |
| }, | |
| "eval: [3] gen:cross_artefact": { | |
| "accuracy": 0.677, | |
| "n": 31 | |
| }, | |
| "eval: [3] gen:dates": { | |
| "accuracy": 0.8, | |
| "n": 10 | |
| }, | |
| "eval: [3] gen:definition_scope": { | |
| "accuracy": 0.667, | |
| "n": 12 | |
| }, | |
| "eval: [3] gen:exception": { | |
| "accuracy": 1.0, | |
| "n": 15 | |
| }, | |
| "eval: [3] gen:judge_action": { | |
| "accuracy": 0.714, | |
| "n": 7 | |
| }, | |
| "eval: [3] gen:lookup_chain": { | |
| "accuracy": 0.7, | |
| "n": 10 | |
| }, | |
| "eval: [3] gen:missing_fact": { | |
| "accuracy": 0.621, | |
| "n": 29 | |
| }, | |
| "eval: [3] gen:nested_exception": { | |
| "accuracy": 0.692, | |
| "n": 13 | |
| }, | |
| "eval: [3] gen:numbers": { | |
| "accuracy": 1.0, | |
| "n": 1 | |
| }, | |
| "eval: [3] gen:precedence": { | |
| "accuracy": 0.909, | |
| "n": 11 | |
| }, | |
| "eval: [3] gen:rubric": { | |
| "accuracy": 0.667, | |
| "n": 3 | |
| }, | |
| "eval: [3] gen:running_total": { | |
| "accuracy": 0.826, | |
| "n": 23 | |
| }, | |
| "eval: [3] gen:surface_trap": { | |
| "accuracy": 0.0, | |
| "n": 1 | |
| }, | |
| "eval: [3] gen:tie_break": { | |
| "accuracy": 0.826, | |
| "n": 23 | |
| }, | |
| "eval: [3] gen:underdetermined": { | |
| "accuracy": 1.0, | |
| "n": 1 | |
| }, | |
| "eval: [3] gen:version_in_force": { | |
| "accuracy": 0.704, | |
| "n": 27 | |
| }, | |
| "eval: [3] gen:withdrawn_instruction": { | |
| "accuracy": 0.75, | |
| "n": 8 | |
| }, | |
| "eval: [4] adequacy_hs2": { | |
| "accuracy": 0.739, | |
| "n": 234 | |
| }, | |
| "eval: [5] gen:adequacy": { | |
| "accuracy": 0.788, | |
| "n": 302 | |
| }, | |
| "eval: boardgame": { | |
| "accuracy": 0.821, | |
| "n": 900 | |
| }, | |
| "eval: contractnli": { | |
| "accuracy": 0.865, | |
| "n": 1026 | |
| }, | |
| "eval: held-out short tasks": { | |
| "accuracy": 0.65, | |
| "ece": 0.06, | |
| "n": 6000, | |
| "nll": 0.851 | |
| }, | |
| "eval: hotpotqa (held out)": { | |
| "accuracy": 0.746, | |
| "n": 959 | |
| }, | |
| "eval: musique": { | |
| "accuracy": 0.882, | |
| "n": 1199 | |
| }, | |
| "eval: musique, answerable": { | |
| "accuracy": 0.886, | |
| "n": 599 | |
| }, | |
| "eval: musique, unanswerable": { | |
| "accuracy": 0.877, | |
| "n": 600 | |
| } | |
| }, | |
| "jevbench": [ | |
| { | |
| "accuracy": 0.7619047619047619, | |
| "arm": "w4096", | |
| "brier": 0.32261680428571426, | |
| "ece": 0.06391125541125536, | |
| "n": 231, | |
| "n_correct": 176, | |
| "schema_validity_strict": 1.0, | |
| "served": "these files", | |
| "window": 4096 | |
| } | |
| ], | |
| "name": "hobson-2b-v21", | |
| "role": "final", | |
| "run_id": "v21b-s5" | |
| } |