allenai/AstaBrief_8B
text-generation model by allenai
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.
AstaBrief-8B is a model trained to turn a research question and retrieved scientific literature excerpts into a cited report using only supervised fine-tuning and offline direct preference optimization. The model is initialized from AstaBrief-8B-SFT and fine-tuned on AstaBriefDPOMix, a collection of real user queries with two reports per query and preference judgements over those report pairs. Reports are generated from both multi-step Asta ScholarQA and single-step report generation pipelines, using a variety of backing models: Claude 3.5 Sonnet, Claude 3.7 Sonnet, o3, o4-mini, GPT-4.1, DeepSeek-V3 and DeepSeek-R1. Two judge models – GPT-4.1 and DeepSeek-R1 – compared each pair and picked a winner. We ensured that LLM judges were aligned with human preferences (95% agreement) and only kept pairs where both judges agreed. For a detailed overview of the project, see our blog. Following is an example inference code snippet: Our DPO training process improves performance over the SFT checkpoint as…
Read the full model card ↗ · Preview checked 2026-10-06T06:39:01.135Z
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
allenai/AstaBrief_8B is a text-generation model repository published by allenai on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 1,294
- Cumulative likes
- 51
- Hugging Face trending score
- 49
- Reported safetensors parameters
- Not reported
- Architecture
- Qwen3ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-02-09T17:13:01.000Z
- Last modified
- 2026-10-03T18:55:16.000Z
Compatibility and lineage
Reported languages: en
Reported base models: allenai/AstaBrief_8B_SFT
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 2026-10-06T06:38:55.388Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.