opencerebral/Boris-2-Think
text-generation model by opencerebral
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Hugging Face | Wiki | License: Apache 2.0 | Authors: OpenCerebral Boris-2-Think is Boris-2, a 144M-parameter model trained from scratch on a single NVIDIA V100, fine-tuned to write a short reasoning trace inside tags before giving a final answer. The traces come from OpenThink, an OpenCerebral distillation set of 43k short, self-consistency-checked reasoning traces written for models this size. It is a question-answering model: it answers a question with … and a Final answer: line. It is not a general chat assistant; for conversation use Boris-2-Instruct. Zero-shot, float32, lm-evaluation-harness 0.4.12 (the Open SLM Leaderboard's settings). ArithMark-3 uses the leaderboard's own bencharithmark-3.py (unmodified, default settings). All numbers are in benchmarkscomparison.csv. The Index is the Open SLM Leaderboard formula: (N(HellaSwag,25) + N(mean(ARC-E, ARC-C),25) + N(PIQA,50) + 0.65 N(ArithMark-3,25)) / 3.65, with N(v,c) = 100(v-c)/(100-c). The gain is in reasoning and science: ARC-Easy +4.2, ARC-Challenge +2.8, ArithMark-3 +4.1, SciQ +2.0. HellaSwag and PIQA…
Read the full model card ↗ · Preview checked 2026-11-12T09:06:17.369Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
opencerebral/Boris-2-Think is a text-generation model repository published by opencerebral on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-generation
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 144,192,782
- Architecture
- Boris2ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-12T06:41:31.000Z
- Last modified
- 2026-11-12T06:53:13.000Z
Compatibility and lineage
Reported languages: en
Reported base models: opencerebral/Boris-2
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-12T06:57:10.640Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.