d1-2B RAG Verifier decision model
d1-2B RAG Verifier checks whether an answer is supported by its source. Read its RAGTruth results, threshold selection and comparison limits.
By landtml · Weights upload: 8 Nov 2026
A d1-2B LoRA for checking whether a supplied answer is supported by its source. It returns one response-level support probability, without identifying unsupported spans. Use the recorded source/request/answer fields and the exact question from the card.
Quick answers
What is d1-2B RAG Verifier by landtml?
d1-2B RAG Verifier: A d1-2B LoRA for checking whether a supplied answer is supported by its source.
Who makes d1-2B RAG Verifier?
Are d1-2B RAG Verifier's weights open?
d1-2B RAG Verifier: Merged BF16 weights, LoRA adapter, Q8_0 GGUF and scoring records Licence: LFM Open License v1.0
Facts
- Size
- 1.9B
- Inputs
- English source, request and generated answer
- Licence
- LFM Open License v1.0
- Access
- Merged BF16 weights, LoRA adapter, Q8_0 GGUF and scoring records
- Evaluation scope
- RAGTruth; training sources capped at 12,000 characters, with longer inputs unevaluated
Claims and sources
- The maker reports F1 81.5, AUROC 0.936 and ECE 0.030 on 2,700 RAGTruth responses. Checkpoint and threshold 0.56 were selected on document-grouped development data. The base comparison reports F1 70.9 but uses Q8_0 llama.cpp while the fine-tune uses BF16. Base-training overlap is unknown; third-party table rows use their own papers and code. vendor reportedsource
Links
Source: Card, weights and evaluation → Source: Scoring code → Source: Licence →
Related projects
No related projects are listed in the registry.