The story so far
Weights, every dated article, and repo commits on one rail.
27 repo commits since the weights landed
Teal is the weights (2026-09-22), grey ticks are repo commits.
bosun-v3.1-1.7b
Hanno-Labs Apache 2.0 out 33 days ago
Text in, text out.
Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 839 · #596 of 619 tracked
Do people use it?839downloads, 30 days#596 of 619 we track · below the median+1 likes, downloads −45% this week9 likesHugging Face2026-10-24
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 1 quantized builds and 6 Spaces.
- As a service0no API provider listed
- On own hardware1quantized builds
- Built on00 fine-tunes · 0 adapters · 0 merges
- In apps6Hugging Face Spaces
Top Spaces running it: multimodalart/jev-decision-index ♥ 802
What people built on it
1 derivative on the Hub. Which build to run, by runtime: the most downloaded in each class.
1 derivative on the Hub
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
Benchmarks
8 rows
Benchmarks 8 rows
measured third-party leaderboard rowauthor-reported number from the model card or eval files (8)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported DecisionBench | 84.90% percent | — | model author | 2026-10-07 |
| author-reported DecisionBench | 84.90% percent | primary accuracy | model author | 2026-10-07 |
| author-reported DecisionBench | 0.05 | ECE | model author | 2026-10-07 |
| author-reported DecisionBench | 0.48 | NLL | model author | 2026-10-07 |
| author-reported DecisionBench | 100.00% percent | coverage | model author | 2026-10-07 |
| author-reported DecisionBench primitive | 92.19% percent | binary classification | model author | 2026-10-07 |
| author-reported DecisionBench primitive | 84.22% percent | candidate selection | model author | 2026-10-07 |
| author-reported DecisionBench primitive | 63.84% percent | ordinal scoring | model author | 2026-10-07 |
What the card says
2 cited sentences
Summary generated, cited
Bosun v3.1 1.7B is a LoRA fine-tune of the Qwen/Qwen3-1.7B base model designed for typed decisions.[1] The model returns a probability distribution over valid choices and supports up to 255 runtime choices plus a null slot.[2]
- “Bosun 3.1 1.7B is a LoRA fine-tune of `Qwen/Qwen3-1.7B`”
- “supports up to 255 runtime choices plus a null slot”
Generated 2026-10-07 15:19 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Use-case evidence
2 use cases
What it is good at 2 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Facts
15 fields
Listed in Decision models
Facts
- License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
- Created 2026-09-22, last modified 2026-09-23. (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | BosunForDecision |
| Model type | bosun |
| Dtype | bfloat16 |
| MoE | no |
| Languages | en |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Decision facts
catalog
Decision-model catalog curated
| How it was made | LoRA + new scoring/pointer head |
|---|---|
| Lineage bucket | F - fine-tune of an open model (public/synthetic data) |
| Lineage evidence | board file inspection (adapter/head/weight files) + HF base_model field |
| Base model | Qwen/Qwen3-1.7B-Base |
| DI 0.2.1 score | 20.10 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.1302 |
| Median latency | 40.3 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/Hanno-Labs/bosun-v3.1-1.7b |
All variants
1 variant
Lineage
Base model: Qwen/Qwen3-1.7B
quantized: 1
Top variants (1 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| Hanno-Labs/bosun-v3.1-1.7b-GGUF | quantized | GGUF | — | — | apache-2.0 | Hanno-Labs | 0 | 395 |
Repository changelog
27 commits
Repository changelog 27 commits
| Date | Commit | SHA |
|---|---|---|
| 2026-09-23 | Link Bosun 1.7B GGUF weights from model card | 1d8dc82 |
| 2026-09-22 | Add Apache-2.0 license and Clause Logic attribution | fd6b47c |
| 2026-09-22 | Update README.md | d9e6386 |
| 2026-09-22 | add Transformers decision model loader | 8c715a3 |
| 2026-09-22 | Remove training-only artifacts from Bosun 3.1 1.7B | b25583e |
| 2026-09-22 | Package Bosun 3.1 1.7B for inference | 45ed354 |
| 2026-09-22 | Improve Bosun 3.1 1.7B model card | 4fe7f14 |
| 2026-09-22 | Upload checkpoints/resume.pt with huggingface_hub | 2ef2d97 |
| 2026-09-22 | Upload checkpoints/resume.pt with huggingface_hub | 84d0f61 |
| 2026-09-22 | Upload checkpoints/resume.pt.sha256 with huggingface_hub | 0f2f9a6 |
| 2026-09-22 | Upload artifact.sha256 with huggingface_hub | 8ba875f |
| 2026-09-22 | Upload training_manifest.json with huggingface_hub | 35aa815 |
| 2026-09-22 | Upload tokenizer/vocab.json with huggingface_hub | 5cfe0d5 |
| 2026-09-22 | Upload tokenizer/tokenizer_config.json with huggingface_hub | 9cc0d6f |
| 2026-09-22 | Upload tokenizer/tokenizer.json with huggingface_hub | 119d374 |
| 2026-09-22 | Upload tokenizer/special_tokens_map.json with huggingface_hub | 7b05b51 |
| 2026-09-22 | Upload tokenizer/merges.txt with huggingface_hub | ef2e2c7 |
| 2026-09-22 | Upload tokenizer/chat_template.jinja with huggingface_hub | 730f8c2 |
| 2026-09-22 | Upload tokenizer/added_tokens.json with huggingface_hub | ea56556 |
| 2026-09-22 | Upload serving.json with huggingface_hub | 38b8011 |
| 2026-09-22 | Upload manifest.json with huggingface_hub | 0d08673 |
| 2026-09-22 | Upload decision_embeddings.safetensors with huggingface_hub | 95c858f |
| 2026-09-22 | Upload adapter/adapter_model.safetensors with huggingface_hub | b16592e |
| 2026-09-22 | Upload adapter/README.md with huggingface_hub | 96d9492 |
| 2026-09-22 | Upload adapter/adapter_config.json with huggingface_hub | fca2231 |
| 2026-09-22 | Upload README.md with huggingface_hub | c9d7d99 |
| 2026-09-22 | initial commit | aa6fa04 |
Similar models
3 models
Similar models
- kev-4b permissive license
- Bespoke-Nimble-9B permissive license
- kev-9b permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:44 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:19 UTC · Last verified 2026-10-25
Follow bosun-v3.1-1.7b
Watch this model
- /feeds/models/Hanno-Labs--bosun-v3.1-1.7b.xml(RSS 2.0) · every change to bosun-v3.1-1.7b
- /feeds/families/Hanno-Labs--bosun-v3.1.xml(RSS 2.0) · every change across the bosun-v3.1 family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.