---
license: apache-2.0
base_model: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
tags: [claim-extraction, fact-checking, misinformation, contradiction-detection, json, qlora, unsloth]
language: [en]
---

# Claim Extractor (Qwen2.5-3B, QLoRA, distilled from 7B)

Fine-tuned to read English text and emit **strict JSON**: a summary, publication date (if present),
keywords, typed/categorized **claims** with verbatim **evidence spans**, and **contradictions** between
claims. Built for rumor / fact-checking pipelines.

## Output schema
```json
{"summary": "...", "publication_date": "ISO date or null", "keywords": ["..."],
 "claims": [{"id": 0, "claim": "...", "claim_type": "fact|statistic|opinion|prediction|speculation|rhetoric|other",
              "category": "...", "importance": "high|medium|low",
              "stance": "asserted|denied|hedged|attributed", "evidence_span": "verbatim", "confidence": 0.0}],
 "contradictions": [{"claim_a": 0, "claim_b": 1, "relation": "contradiction|tension", "explanation": "..."}]}
```

## Files
- `merged_16bit/` — full fp16 model (HF format)
- `Qwen2.5-3B-Instruct.Q4_K_M.gguf` — Q4_K_M GGUF for llama.cpp (runs on a 4 GB GPU)
- `lora_adapter/` — LoRA adapter only
- `claim.gbnf` + `prompt.txt` — grammar + instruction for **guaranteed-valid** JSON via llama-cpp-python

## Quick use (llama.cpp, grammar-constrained → always valid JSON)
```bash
pip install llama-cpp-python
# load Qwen2.5-3B-Instruct.Q4_K_M.gguf with claim.gbnf as the grammar and prompt.txt prepended to your text
```

## Training
Distilled from `unsloth/Qwen2.5-7B-Instruct-bnb-4bit`. Data: ag_news (teacher-labeled) + SNLI (contradiction pairs) +
LIAR (misinformation) + teacher-synthesized adversarial passages. QLoRA r=32, 3 epochs.

## Benchmarks
```json
{
  "contradiction_recall": 0.75,
  "evidence_verbatim_rate": 1.0,
  "date_extraction_rate": 1.0
}
held_out_validity = 1.0, unseen_validity = 1.0
```