GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Meclin
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Meclin
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
The adapter modifies the query, key, value, and output projections of every attention block and the MLP projection layers of the frozen 4B-parameter backbone. Only the low-rank matrices are trained; the base weights remain frozen. The adapter is loaded alongside the base model in bfloat16 precision at inference.
TamilRAV is released as an editorial assistance tool for Tamil fact-checking newsrooms, platform trust-and-safety teams, and human-supervised verification pipelines. The intended workflow is retrieval-augmented: retrieve candidate evidence for a claim (in CDPVA: Qwen3-Embedding-0.6B dense retrieval over a Qdrant index, top-20, reranked to top-3 with BGE-Reranker-v2-m3), then prompt TamilRAV with the claim and the reranked passages.
For best results, use self-consistency decoding as in the paper: sample three generations at temperatures 0.3, 0.5, and 0.7, take the majority-vote verdict, and average the three confidence scores.
TamilRAV serves as the reasoning path of the full CDPVA system, in which its verdict, pooled confidence, and evidence count are reconciled with a discriminative multimodal classifier through a rule-based verification gate. The full system reaches macro-F1 92.9 on the TamilFacts-X evaluation set.
Keep a human in the loop for any consequential decision. Present the model's cited evidence and reasoning trace alongside its verdict so reviewers can audit the basis for each prediction. Recalibrate the confidence threshold on an in-domain validation split before deployment, particularly when the retrieval corpus differs from TamilFacts-X.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torchbase_id = "Qwen/Qwen3.5-4B"adapter_id = "[TODO: your-org/TamilRAV]"tokenizer = AutoTokenizer.from_pretrained(base_id)model = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id)model.eval()# Use the exact prompt template released with the paper/repository.# Structure: the Tamil claim followed by the reranked evidence passages,# requesting the four structured output fields.prompt = build_prompt(claim_ta, evidence_passages) # see repository for the template# Self-consistency decoding as used in the paperverdicts, confidences = [], []for temp in (0.3, 0.5, 0.7):inputs = tokenizer(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=temp)text = tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)v, c = parse_structured_output(text) # regex parser for verdict/confidence fieldsverdicts.append(v); confidences.append(c)final_verdict = max(set(verdicts), key=verdicts.count) # majority votefinal_confidence = sum(confidences) / len(confidences) # mean pooling
The adapter is fine-tuned on the training partition (15,497 claims) of TamilFacts-X, a 17,271-claim multimodal Tamil fact-checking benchmark built from published fact-check articles and annotated under a four-class veracity taxonomy (True / False / Misleading / Altered). Each supervised instance serializes the claim together with its reranked evidence passages as input, and the four structured output fields (verdict, Tamil explanation, confidence in [0, 1], reasoning trace) as the target. [TODO: link the dataset card]
Supervised fine-tuning with LoRA. The training objective combines the standard autoregressive cross-entropy loss over the serialized target with a Brier-score regularizer on the confidence field, which penalizes the squared deviation between the stated confidence and the correctness of the predicted verdict.
Evaluated on the balanced 608-claim TamilFacts-X evaluation set (152 claims per class). Metric: macro-averaged F1 over the four classes. Evidence at test time is retrieved from the fact-check corpus (Qwen3-Embedding-0.6B + Qdrant, top-20; BGE-Reranker-v2-m3, top-3). Self-consistency (SC) denotes three samples at T ∈ {0.3, 0.5, 0.7} with majority-vote verdicts and mean-pooled confidence. The leave-one-out (LOO) condition removes each claim's own source article from its retrieval pool.
| Configuration | Macro-F1 |
|---|---|
| TamilRAV, single sample | 78.3 |
| TamilRAV + self-consistency | 82.7 |
| TamilRAV + SC, leave-one-out retrieval | 67.7 |
| Full CDPVA system (with discriminative path + gate) | 92.9 ± 0.6 |
Per-class F1 of TamilRAV + SC on the evaluation set: True 88.0, False 78.5, Misleading 75.1, Altered 89.4.
For reference, the strongest zero-shot text-prompted frontier LLM baseline evaluated in the paper reaches 62.5 macro-F1 on the same set (under a non-like-for-like, retrieval-free condition).
With retrieval grounding and self-consistency, a 4B-parameter LoRA-adapted model substantially outperforms zero-shot frontier LLMs on Tamil claim verification, and its structured, evidence-cited outputs make each verdict auditable. Its standalone accuracy depends significantly on retrieval quality, which is why it is deployed inside CDPVA alongside a discriminative classifier and a verification gate.
Qwen3.5-4B decoder-only transformer (rotary positional embeddings, SwiGLU activations, large multilingual vocabulary) with LoRA adapters on all attention Q/K/V/O and MLP projection matrices. Objective: autoregressive cross-entropy over structured verification outputs plus a Brier-score confidence regularizer.
[TODO: GPU model and VRAM]
BibTeX:
[TODO]
[TODO: email or HF discussion link]