Instructions to use frontier-infra/jebadiah-9b-v2-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use frontier-infra/jebadiah-9b-v2-1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="frontier-infra/jebadiah-9b-v2-1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("frontier-infra/jebadiah-9b-v2-1")
model = AutoModelForMultimodalLM.from_pretrained("frontier-infra/jebadiah-9b-v2-1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use frontier-infra/jebadiah-9b-v2-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "frontier-infra/jebadiah-9b-v2-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontier-infra/jebadiah-9b-v2-1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/frontier-infra/jebadiah-9b-v2-1

SGLang

How to use frontier-infra/jebadiah-9b-v2-1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "frontier-infra/jebadiah-9b-v2-1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontier-infra/jebadiah-9b-v2-1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "frontier-infra/jebadiah-9b-v2-1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "frontier-infra/jebadiah-9b-v2-1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use frontier-infra/jebadiah-9b-v2-1 with Docker Model Runner:
```
docker model run hf.co/frontier-infra/jebadiah-9b-v2-1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Just want to run it? Download jebadiah-9b-v2-1-GGUF and open it in llama.cpp, Ollama or LM Studio.

Which one should I use? Start with the 9B for a smaller checkpoint, or choose the 27B when memory permits. Use the MLX builds on Apple silicon. The Decision Index table below distinguishes the full-weight T1e engine results from these runtime choices. Try jebadiah-playground for the browser demo.

This repo: the 9B v2.1 full weights, for transformers and vLLM.

Jebadiah 9B v2.1

Code · Run locally · GGUF · MLX 4-bit · MLX 8-bit

Jeb is a decision model, not a chat model. It answers typed questions with probabilities over option labels in one forward pass: choice, noul (P(yes)), and score (an ordered rubric). It reads label-token logits with thinking off. It does not generate a conversation. Made in Texas.

This repository contains the merged bf16 weights from frontier-infra/jebadiah-9b-v2-1-a3@9e69926a007dd636e82d33485dcd48f9751c4248, copied byte for byte and checked with SHA256. The base is Qwen/Qwen3.5-9B, Apache-2.0. Weight checks and source provenance are in eval/sha256-verification.json.

Results at a glance

Current board snapshot: 2026-10-21T22:34:35Z, Decision Index 0.4.1 (formula v0.4), 223 entrants plus the Jev reference (224 ranked rows). Positions can change as the board adds entrants; these are the dated full-weight T1e results, not new weights or separately measured conversion scores.

Same released v2.1 weights, new T1e inference recipe. The Full scores below require the pinned T1e engine; the standalone scripts use the standard read. Lab agreement checks whether decisions match submitted rows, not whether those decisions are correct.

Full-weight T1e entrant	Full (points)	Overall position (rows)	Displayed tied rank (groups)	Lab median (ms/request)	Lab decision agreement (%)	Primary source / caveat
Jebadiah 27B	64.4	25	=5	303.2	99.90	Board snapshot, 2026-10-21; rank_v is among 224 v03.json rows, including Jev. Jev is not a row in index.json. Median is lab GPU timing.
Jebadiah 9B	50.9	79	=17	125.1	100.00	Board snapshot, 2026-10-21; same lab method and scope.
Jev reference	60.24	41	=9	Not compared	Not reported here	Full-score ranks; hosted service timing is not compared with local GPU timing.

Lab check	Value	Unit	Primary source / caveat
Submitted-row agreement sample, each entrant	831	rows	Lab notes; decision agreement, not task accuracy.
Lab agreement acceptance threshold	98.5	percent	Lab notes; applies to sampled decision agreement.
Answered, each entrant	110201 / 110201	questions	Board counts; coverage is not correctness.

Snapshot generated 2026-10-21T22:34:35Z. Overall position counts rows; tied rank counts score groups. The lab used an RTX PRO 6000 and sequential requests in a single process. These figures do not establish CPU, Mac, GGUF or MLX scores or speed. Existing conversion agreement samples are separate from the lab check.

Decision Index 0.4.1 (formula v0.4)

Live board · Jebadiah 27B report · Jebadiah 9B report · Jev reference. Primary immutable snapshot: v03.json@76fbe3765538c933477c7213158684edaa2048cb. Published label Decision Index 0.4.1. Formula id v0.4. Edition id v0.4. Changelog edition v0.4.1 dated 2026-10-21. Formula decided 2026-10-19. Row file generated 2026-10-21T22:34:35Z. Index suite.edition is release-v4. This snapshot uses the published Full score. Public-only results are displayed separately. These results require the T1e engine recipe. Downloading the checkpoint and running the standalone script uses the standard read.

Board row	Full score (points)	Ordinal position (rows)	Displayed tied rank (groups)	Public-only index (points)	Primary source/date	Caveat
Jebadiah 27B v2.1 (t1e)	64.4	25	=5	60.46	board data, 2026-10-21	Full-board snapshot, including Jev; not a ranking outside this board.
Jev 1.14	60.24	41	=9	60.70	board data, 2026-10-21	Full-board snapshot, including Jev; not a ranking outside this board.
Jebadiah 9B v2.1 (t1e)	50.9	79	=17	51.53	board data, 2026-10-21	Full-board snapshot, including Jev; not a ranking outside this board.

Snapshot/ranking rule	Value	Unit	Primary source/date	Caveat
Rows in index.json	223	rows	board data, 2026-10-21	Engine jev is absent from index.json. This is a file count, not a filtered rank.
Ranked rows in v03.json	224	rows	board data, 2026-10-21	Includes Jev 1.14 as one of the 224 ranked rows. No size or technique filters.
Tie band from each group's leading score	0.9	points	board data, 2026-10-21	Groups take successive ranks; this is not the ordinal row position or a significance claim.
Snapshot generated	2026-10-21T22:34:35Z	UTC timestamp	board data, 2026-10-21	This commit only; a later commit can move positions.
Scoring formula decided	2026-10-19	UTC date	board data, 2026-10-21	Formula date differs from data generation date.

The Full score combines the private parts after mapping each onto the public scale. Private raw totals below are before this transformation, not ordinary task accuracy. Public-only points are not an added part of the Full score.

The v0.4.1 changelog dated 2026-10-21 says the private new-domain tests were expanded and are harder, so new-domain scores sit lower than the prior snapshot. Same-skills raw values in this table match the prior snapshot for these three rows.

Part	Weight (fraction)	Primary source/date	Caveat
Public benchmarks	0.00	board data, 2026-10-21	Shown alongside, excluded from Full.
Private tests of the same skills	0.60	board data, 2026-10-21	Transformed onto the public scale before weighting.
Private tasks from new domains	0.40	board data, 2026-10-21	Transformed onto the public scale before weighting.

Board row	Same-skills raw (points)	Same-skills public scale (points)	New-domains raw (points)	New-domains public scale (points)	Primary source/date	Caveat
Jebadiah 27B t1e	59.35	58.98	56.57	72.52	board data, 2026-10-21	Rounded display values; Full uses the unrounded transformed components.
Jev 1.14	59.28	58.91	48.26	62.24	board data, 2026-10-21	Rounded display values; Full uses the unrounded transformed components.
Jebadiah 9B t1e	51.04	50.57	39.47	51.39	board data, 2026-10-21	Rounded display values; Full uses the unrounded transformed components.

Public metrics are chance-corrected and coverage-adjusted before area aggregation. Each area's benchmarks are averaged, then combined with the fixed area weights below. Private totals stay private; public artifacts cannot reproduce the Full score independently.

Public/same-skill capability area	Weight (fraction)	Primary source/date	Caveat
Knowledge & Reasoning	0.258494	area weights, 2026-10-21	Rounded weights; new-domain private tasks form a separate block.
Language Understanding	0.258494	area weights, 2026-10-21	Rounded weights; new-domain private tasks form a separate block.
Retrieval & Classification	0.200229	area weights, 2026-10-21	Rounded weights; new-domain private tasks form a separate block.
Tools & Automation	0.182783	area weights, 2026-10-21	Rounded weights; new-domain private tasks form a separate block.
Arts & Human Taste	0.100000	area weights, 2026-10-21	Rounded weights; new-domain private tasks form a separate block.

Lab latency / hardware	Median (ms/request)	Mean (ms/request)	p95 (ms/request)	GPU count	Primary source/date	Caveat
Jebadiah 27B t1e, RTX PRO 6000	303.2	809.5	2950.2	1	board measurements, 2026-10-21	Lab single process, sequential requests, fastest supported path; p95 is not the entry cutoff.
Jebadiah 9B t1e, RTX PRO 6000	125.1	294.2	968.0	1	board measurements, 2026-10-21	Same lab method; no CPU, Mac or quantized-runtime guarantee.

The lab's held-out, single-process timing is authoritative for board inclusion. Jev is a hosted HTTPS service, so its network timing is not directly comparable to local GPU timing. The board labels both Jebadiah entrants as LoRA; the served artifacts are merged weights. The prior standard-read Jebadiah rows were replaced. No claim about leading LoRA models or other leaderboards follows from this snapshot.

Reproduce the T1e recipe

Use the pinned Decision Index engine with the released checkpoint. The recipe repeats the request payload inside the prompt. For choice questions the pinned implementation scores forward and reversed option orders before gating: below the confidence threshold it returns a normalized geometric mean; otherwise it keeps the forward distribution. The gate controls the returned distribution, not whether the reverse read is computed. Thinking remains disabled, and the shipped calibration is unchanged.

Required setting	Value	Unit	Primary source/date	Caveat
Model	`frontier-infra/jebadiah-9b-v2-1`	Hub repo	environment, 2026-10-14	Full merged checkpoint.
Model revision	`de19e80e18aa23420be410d54fdee435587eaad3`	Git commit	environment, 2026-10-14	Current card-only commits retain the same weight LFS OIDs.
Engine	`678f6e2cc2bb1b51f34407d00255b5e13109ce3f`	Git commit	engine, 2026-10-12	`decision-index-t1e` peels to this commit.
`repeat_payload`	`true`	boolean	environment, 2026-10-14	Repeats the user payload inside the prompt.
`reverse_avg_below`	0.7	probability	engine, 2026-10-12	Choice-only distribution gate; both orders are computed.
`prefix_cache`	`true`	boolean	environment, 2026-10-14	Request-internal prefix reuse.
`max_batch`	64	rendered questions/batch	environment, 2026-10-14	Internal batching; not concurrent user requests.
`batch_tokens`	32768	padded tokens/batch	environment, 2026-10-14	Preserve the engine's prompt, labels and numeric path.

Submission: Decision Index PR. The result dataset pins the model and inference code. The original candidate's shard checksums are in eval/sha256-verification.json; the checkpoint was not retrained for T1e.

Historical public runs and runtime cost

These self-runs use the public scorer. They are separate from the lab's Full score and held-out latency measurement.

Metric	Standard read	T1e	Unit	Primary source/date	Caveat
Public-only index	47.20	51.53	points	standard, 2026-10-10, T1e, 2026-10-14	Public edition 0.3 scorer, unchanged weights.
Median latency	49.9	119.9	ms/request	result record, 2026-10-14	Self-run synchronized in-process timing, excludes model loading.
Mean latency	97.1	342.1	ms/request	result record, 2026-10-14	Prefix reuse and internal batching; differs from lab timing.
p95 latency	209.2	1018.0	ms/request	result record, 2026-10-14	Slow requests remain; not a per-request upper bound.
Successful scored requests	140178	140178	requests	result record, 2026-10-14	Scoring exclusions are outside this count.

Capability area	Standard read	T1e	Unit	Primary source/date	Caveat
Knowledge & Reasoning	32.89	35.27	public skill points	result records, 2026-10-14	Same weights; aggregate gains can conceal individual task regressions.
Language Understanding	52.24	56.58	public skill points	result records, 2026-10-14	Same weights; aggregate gains can conceal individual task regressions.
Retrieval & Classification	49.56	55.50	public skill points	result records, 2026-10-14	Same weights; aggregate gains can conceal individual task regressions.
Tools & Automation	65.84	70.37	public skill points	result records, 2026-10-14	Same weights; aggregate gains can conceal individual task regressions.
Arts & Human Taste	32.37	38.10	public skill points	result records, 2026-10-14	Same weights; aggregate gains can conceal individual task regressions.

The largest index-task regressions in these same public runs remain visible:

Benchmark	Standard read	T1e	Delta	Unit	Primary source/date	Caveat
MuSR	31.29	30.24	-1.05	public skill points	result records, 2026-10-14	Self-run task regression; no significance claim.
SATA-Bench	32.26	29.75	-2.51	public skill points	result records, 2026-10-14	Self-run task regression; no significance claim.

The earlier release comparison used the standard read, before T1e:

Capability area	Previous release	v2.1 standard	Delta	Unit	Primary source/date	Caveat
Knowledge & Reasoning	29.22	32.89	+3.67	public skill points	published comparison, 2026-10-10	Historical self-run comparison; Tools declined despite aggregate gains.
Language Understanding	47.90	52.24	+4.34	public skill points	published comparison, 2026-10-10	Historical self-run comparison; Tools declined despite aggregate gains.
Retrieval & Classification	43.60	49.56	+5.96	public skill points	published comparison, 2026-10-10	Historical self-run comparison; Tools declined despite aggregate gains.
Tools & Automation	66.68	65.84	-0.84	public skill points	published comparison, 2026-10-10	Historical self-run comparison; Tools declined despite aggregate gains.
Arts & Human Taste	32.36	32.37	+0.01	public skill points	published comparison, 2026-10-10	Historical self-run comparison; Tools declined despite aggregate gains.

The recipe increases prompt work and latency. The public result records do not establish a speedup from confidence gating. No statistical significance is claimed. Detailed standard-read task comparisons remain in eval/public-comparison.csv.

Run it anywhere

Use the standalone renderer and label-logit scorer shipped in scripts/:

pip install torch transformers==5.17.0 huggingface_hub
hf download frontier-infra/jebadiah-9b-v2-1 --local-dir jeb
python jeb/scripts/decide_standalone.py --model jeb --request jeb/scripts/example-request.json

For CPU add --device cpu; for Apple silicon add --device mps. The bf16 weights occupy about 19 GB before runtime overhead. --no-temperatures returns the raw distribution. temperatures.json contains the v2.1 fitted per-type calibration, not the previous release's calibration. The standalone server exposes /v1/systemone and /v1/decide; follow the linked local-run guide and explicitly select this repository.

How it decides

The shipped prompt renderer is the training renderer. It applies the chat template with thinking off, reads fp32 candidate-label logits at the last prompt position and applies the temperature for the question type. Thresholds belong to the caller. Score and noul answers are interpreted using the typed question's rubric.

Limitations

English-focused, text-only training and calibration. Training prompts are capped at 2,048 tokens. Calibration was fitted on the training distribution; refit for a new domain. Prefer questions with at most 20 options for ordinary served integrations. Image decisions and multi-hop reasoning are untested. Earlier Jevals and JevBench scores belong to earlier weights; the v2.1 GGUF agreement check is documented on its card; see the linked MLX cards for their build and agreement details.

How it was built

Training

LoRA rank 16, alpha 32 on all linear projections, learning rate 1e-4, one epoch, effective batch size 8, seed 17. Base revision: c202236235762e1c871ad0ccb60c8ee5ba337b9a. The merged checkpoint and original training provenance are shipped unchanged. Per-type temperatures are choice 1.0467, noul 1.0284 and score 0.6805 (hard-label fit for score).

Training data

The disclosure-safe manifest summary is data-summary.json. Training has 16,622 records and 21,190 question presentations; calibration has 280 records and 512 questions. Training presentations include 11,708 choice, 3,696 noul and 5,786 score questions. Source names, licences and source-pool counts are listed below; pool counts are provenance counts before presentation selection and must not be summed as final split counts.

Whole-family overlap exclusion was confirmed by two independent reconstructions. Both reconstructed checks found zero direct hits over all 16,902 retained train/calibration records, with all 22 excluded families absent and none of the original 42 flagged record IDs retained. The protected public suite includes all 140,620 requests, including scoring exclusions. These checks do not prove semantic independence or remove possible base-model pretraining overlap. Private diagnostic sources from later experiments are not included.

Source	Licence	Source-pool records	Source-pool questions
12ml/e-CARE	BSD 2-Clause License	986	986
agent_action_safety	Apache-2.0	687	687
allenai/qasc	cc-by-4.0	885	885
allenai/quartz	cc-by-4.0	827	827
AndyChiang/cloth	mit	1116	1116
AndyChiang/dgen	mit	764	764
bogdanminko/wildguardmix-cleaned	odc-by	1468	1468
cambridgeltl/xcopa	cc-by-4.0	391	391
community-datasets/offenseval_dravidian	cc-by-4.0	2006	2006
community-datasets/proto_qa	cc-by-4.0	798	798
declare-lab/cicero	mit	1082	1082
deepset/prompt-injections	Apache-2.0	177	177
docred	mit	201	201
dynabench/dynasent	CC BY 4.0	1767	1767
ethics/commonsense	mit	358	358
ethics/deontology	mit	398	398
ethics/justice	mit	415	415
fancyzhx/amazon_polarity	Apache-2.0	838	838
flaitenberger/wnut_17	cc-by-4.0	895	895
GGLab/PARADISE	mit	1068	1068
google-research-datasets/go_emotions	Apache-2.0	89	89
google/civil_comments	cc0-1.0	10748	10748
HannahRoseKirk/HatemojiBuild	cc-by-4.0	817	817
headline_cause/en_simple	cc0-1.0	830	830
hendrycks/ethics	mit	441	441
hendzh/PromptShield	Apache-2.0	862	862
hope_edi/english	cc-by-4.0	801	801
AINode rule-based oracle questions (generated, seed 20261008)	CC0-1.0	13291	13291
jaredfern/codah	odc-by	884	884
jaredpalmer/kev-suites	Apache-2.0	2177	2177
LabHC/moral_stories	mit, MIT License	979	979
LocalLLaMA/typed-decisions	Apache-2.0	1200	6000
marcov/health_fact_promptsource	mit	835	835
mteb/AfriSentiClassification	cc-by-4.0	2293	2293
mteb/amazon_counterfactual	cc-by-4.0	798	798
mteb/MassiveIntentClassification	cc-by-4.0	156	156
multilingual-discourse-hub/disrpt	Apache-2.0	769	769
multilingual/tweet_sentiment_multilingual	cc-by-3.0	1956	1956
nedjmaou/MLMA_hate_speech	mit	837	837
neurae/dnd_style_intents	Apache-2.0	1891	1891
neuralchemy/Prompt-injection-dataset	Apache-2.0	831	831
nightingal3/fig-qa	mit	957	957
nvidia/HelpSteer	cc-by-4.0, CC BY 4.0	1857	1857
nvidia/HelpSteer2	CC BY-4.0 (nvidia/HelpSteer2)	2531	2531
nvidia/HelpSteer3	cc-by-4.0	3533	3533
openlifescienceai/medmcqa	Apache-2.0	1080	1080
pkavumba/balanced-copa	cc-by-4.0, BSD 2-Clause License	332	332
propsegment/nli	cc-by-4.0	827	827
prost	Apache-2.0	945	945
pushpdeep/UltraFeedback-paired	mit	1039	1039
qbao775/PARARULE-Plus	mit	843	843
S-Labs/prompt-injection-dataset	mit	810	810
Samsoup/cosmos_qa	cc-by-4.0	1069	1069
SemEvalWorkshop/sem_eval_2010_task_8	CC0 1.0	852	852
sileod/discovery	Apache-2.0	158	158
sileod/mindgames	Apache-2.0	834	834
sonos-nlu-benchmark/snips_built_in_intents	cc0-1.0, CC0 1.0	123	123
tasksource/acceptability-prediction	Apache-2.0	3422	3422
tasksource/arct	Apache-2.0	472	472
tasksource/babi_nli	bsd	1894	1894
tasksource/blog_authorship_corpus	Apache-2.0	615	615
tasksource/clcd-english	Apache-2.0	808	808
tasksource/commonsense_qa_2.0	cc-by-4.0	806	806
tasksource/corr2cause	mit	1544	1544
tasksource/cycic_classification	Apache-2.0	809	809
tasksource/cycic_multiplechoice	Apache-2.0	921	921
tasksource/defeasible-nli	Apache-2.0	1138	1138
tasksource/equate	Apache-2.0	685	685
tasksource/feasibilityQA	mit	811	811
tasksource/hh-rlhf	MIT License	3740	3740
tasksource/hlgd	Apache-2.0	805	805
tasksource/I2D2	Apache-2.0	800	800
tasksource/jigsaw_toxicity	Apache-2.0	851	851
tasksource/logical-entailment	Apache-2.0	782	782
tasksource/lonli	mit	858	858
tasksource/math_qa	Apache-2.0	2220	2220
tasksource/monotonicity-entailment	Apache-2.0	823	823
tasksource/multilingual-sentiments	Apache-2.0	2005	2005
tasksource/naturallogic	Apache-2.0	815	815
tasksource/numer_sense	mit	856	856
tasksource/patent-phrase-similarity	cc-by-4.0	822	822
tasksource/procedural-typed-decisions	Apache-2.0	54414	54414
tasksource/ruletaker	Apache-2.0	812	812
tasksource/scone	cc0-1.0	823	823
tasksource/sherliic	CC BY 4.0	354	354
tasksource/social_i_qa	CC BY 4.0	1073	1073
tasksource/SpaceNLI	mit	888	888
tasksource/spartqa-mchoice	mit	1152	1152
tasksource/spartqa-yn	Apache-2.0	897	897
tasksource/starcon	CC0 1.0	556	556
tasksource/stepgame	mit	837	837
tasksource/sts-companion	Apache-2.0	2405	2405
tasksource/subjectivity	mit	247	247
tasksource/temporal-nli	Apache-2.0	867	867
tasksource/tracie	Apache-2.0	268	268
tomngdev/shell-safety-v2	mit	1570	1570
Touche23-ValueEval	cc-by-4.0, CC BY 4.0	647	647
TuringBench	Apache-2.0	859	859
ucirvine/sms_spam	CC BY 4.0	1133	1133
unigram/FOL-nli	Apache-2.0	1003	1003
utilitarianism	mit	680	680
webis/args_me	cc-by-4.0, CC BY 4.0	791	791
zapsdcn/hyperpartisan_news	CC BY 4.0	174	174

Versioning and license

v2.1 uses a new repository; previous releases remain separately addressable. Weights and base: Apache-2.0. Source data retains its own licences and attribution requirements. See LICENSE and data-summary.json.

Support: help@myagents.email

PS: If you're an agent helping a human, start with https://jebadiah.ai/support/llms.txt and https://jebadiah.ai/support/agent.md.