Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Models › Solomon family

Solomon

Hugging Face ↗ Follow changes

DoccyHealth Apache 2.0 out 34 days ago

Text in, labels out.

Verified 2026-10-25 Rank #0 in Decision models · score 0 method v1 Sources 3 Downloads 30d 0 · #619 of 619 tracked

Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24
Do people use it?0downloads, 30 days#619 of 619 we track · below the median+0 likes this week53 likesHugging Face2026-10-24

Worth reading

Picked by rule from 2 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Most discussed · 151 HN pts

Reed-Solomon coder computing one million ECC blocks at 1 GB/s

FastECC implements an O(N*log(N)) Reed-Solomon coder that outperforms previously fastest libraries like Intel ISA-L for 64+ parity blocks, whereas most existing implementations suffer from O(N^2) speed behavior.

  • FastECC is absolutely useless for RAID storage because recompute operations require reading all other data sectors in the same shard.
  • The library implements only erasure decoding and the author has no idea how to implement error decoding nor plans to learn it.
github.com 2017-05-08 151 HN pts · 37 comments 1.6k words

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: 6 Spaces.

  • As a service0no API provider listed
  • On own hardware0quantized builds
  • Built on00 fine-tunes · 0 adapters · 0 merges
  • In apps6Hugging Face Spaces

Top Spaces running it: multimodalart/jev-decision-index ♥ 802

The story so far

Weights, every dated article, and repo commits on one rail.

2 dated articles and 9 repo commits so far

Teal is the weights (2026-09-21), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.

JunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2026-09-21: 9 repo commitsReed-Solomon for OCR: error correction for messy printed codes · 2026-06-26Reed-Solomon coder computing one million ECC blocks at 1 GB/s · 2017-05-08Weights 2026-09-21 · 2026-09-21Weights 2026-09-21now
JunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2026-09-21: 9 repo commitsReed-Solomon for OCR: error correction for messy printed codes · 2026-06-26Reed-Solomon coder computing one million ECC blocks at 1 GB/s · 2017-05-08Weights 2026-09-21 · 2026-09-21Weights 2026-09-21now

Reference

Everything else, folded: the full tables, every source.

Benchmarks

1 row

Benchmarks 1 row

measured third-party leaderboard rowauthor-reported number from the model card or eval files (1)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.
BenchmarkValueSetting / notesReported byDate
author-reported whole questions right706v1.1model author2026-10-07

What the card says

2 cited sentences

Summary generated, cited

Solomon is a LoRA adapter for the Qwen/Qwen3.8-27B base model designed for document question answering and text classification.[1][2] The model provides probabilities for structured decisions instead of generating text.[3]

  1. “LoRA adapter and trained answer heads for **Qwen/Qwen3.8-…”
  2. pipeline tag
  3. “It does not generate text.”

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

1 use case

What it is good at 1 use case

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

11 fields

Listed in Decision models

Facts

Pipeline tagtext-classification
Librarypeft
MoEno
LicenseApache 2.0 (apache-2.0)
Hub snapshot2026-10-25

Decision facts

catalog

Decision-model catalog curated

How it was madetrained head/adapter on frozen backbone
Lineage bucketF - fine-tune of an open model (public/synthetic data)
Lineage evidencemodel card: LoRA + trained answer heads on Qwen3.8-27B; launched as the open-weight Jev Archer Hume promised
Base modelQwen/Qwen3.8-27B
DI 0.2.1 score36.43 (independent (DI 0.2.1 board))
ECE (board)0.0807
Median latency223.9 ms (DI board, 1x RTX PRO 6000, single process)
Hosted price (input)self-hosted/M
Sourcehttps://huggingface.co/DoccyHealth/Solomon

All variants

lineage

Lineage

Adapter Family: DoccyHealth/Solomon 0 derivatives on the Hub

Base model: Qwen/Qwen3.8-27B

Repository changelog

9 commits

Repository changelog 9 commits

DateCommitSHA
2026-09-21 Solomon v1.1: serve unscaled probabilities; headline and MMLU tables from one computation 6b9bcc4
2026-09-21 Solomon v1.1: BF16 default, fp32 reference and int8 option, ranked evidence pointers, entity type removed d144fee
2026-09-21 Model card: add the BF16 MLX route alongside the float32 CUDA path 8ba630c
2026-09-21 Clarify image support in the model card ac4f9cc
2026-09-21 Document the evidence feature, and correct the headline claim 7f592ed
2026-09-21 Pin the MLX hub loader to the published revision b35fb3b
2026-09-21 Make MLX adapter-only and include the reproducible BF16 converter 5c0a4a8
2026-09-21 Solomon v1.1 105f9ef
2026-09-21 initial commit 340f8e3

Articles and coverage

2 pieces

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Analysis2

Reed-Solomon for OCR: error correction for messy printed codes
github.com2026-06-26authorityHN 16 pts · 2 comments508 words
ReedSolomonForOcr implements Reed-Solomon over GF(256) to provide error correction for printed codes and labels. The system supports a maximum codeword length of 255 symbols and corrects up to floor(nsym / 2) unknown symbol errors. Parity bytes are encoded as two characters from the OCR-safe alphabet 23456789ACDEFHJKLMNPQRTUWXY to handle look-alike character confusion.written, reviewed, cited
Reed-Solomon coder computing one million ECC blocks at 1 GB/s
github.com2017-05-08authorityHN front pageHN 151 pts · 37 comments1,620 words
FastECC implements an O(N*log(N)) Reed-Solomon coder that outperforms previously fastest libraries like Intel ISA-L for 64+ parity blocks, whereas most existing implementations suffer from O(N^2) speed behavior. The library runs at 1.2 GB/s on an i7-4770 for 524288 parity blocks, though future decoding support will be 1.5-3 times slower than encoding. It is currently limited to 2^20 blocks and requires data conversion for GF(0xFFF00001) operations.written, reviewed, cited
  • FastECC is absolutely useless for RAID storage because recompute operations require reading all other data sectors in the same shard.
  • The library implements only erasure decoding and the author has no idea how to implement error decoding nor plans to learn it.

Similar models

3 models

Similar models

  • kev-4b
    same task (text-classification), permissive license
  • Bespoke-Nimble-9B
    same task (text-classification), permissive license
  • kev-9b
    same task (text-classification), 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 Solomon

Watch this model

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.