Ainvest Decision 31B v2.0
Ainvest Decision 31B v2.0 scores text options with Gemma 4 weights. Its package includes BF16 weights, conditional input repetition and a CUDA runtime.
By Ainvest-World · Hugging Face weight release: 11 Nov 2026
A text-only Gemma 4 31B fine-tune that scores supplied option tokens without generating an answer. It reads complete inputs twice when they are at most 3,000 tokens before repetition, handling each question separately. The package includes full BF16 weights and its inference code.
Quick answers
What is Ainvest Decision 31B v2.0 by Ainvest-World?
Ainvest Decision 31B v2.0: A text-only Gemma 4 31B fine-tune that scores supplied option tokens without generating an answer.
Who makes Ainvest Decision 31B v2.0?
Facts
- Base
- google/gemma-4-31B-it; full-parameter backbone training with token embeddings and output head frozen
- Inputs
- Text Choice with 2 to 255 options, or Noul; up to 64 questions per request
- Context
- 262,144 rendered tokens per question, including repetition and template; unsupported questions reject the whole request without truncation
- Access
- 16 BF16 weight shards, approximately 62.55 GB before runtime overhead; CUDA package and CLI
- Licence
- Apache-2.0 release; retain base-model and MIT helper notices
Claims and sources
- The maker describes training on more than 2 million cleaned text-decision examples with teacher-generated soft labels. The public score is reused from an earlier full run; publication checks do not constitute a fresh full benchmark. vendor reportedsource
Links
Source: Card and inference package → Source: Licence → Source: Third-party terms → Source: Weight manifest →
Related projects
No related projects are listed in the registry.