license, license_name, license_link, base_model, base_model_relation, library_name, pipeline_tag, tags

license	license_name	license_link	base_model	base_model_relation	library_name	pipeline_tag	tags
other	qwen-research	aa8e725379/LICENSE	Qwen/Qwen2.5-3B-Instruct tanny2109/consensuslab-peer-deference-agreement-qwen2.5-3b-grpo-lora	merge	transformers	text-generation	grpo qwen2 research consensuslab

ConsensusLab Agree-with-Peer — standalone merged 3B model

This contains the complete Qwen2.5-3B-Instruct base weights with the final step-80 Agree-with-Peer GRPO LoRA merged into them. Loading requires Transformers, not a separate PEFT adapter. No additional training was performed during export.

Provenance

• Base: Qwen/Qwen2.5-3B-Instruct
• Exact base revision: aa8e72537993ba99e69dfaafa59ed015b17504d1
• Source adapter: tanny2109/consensuslab-peer-deference-agreement-qwen2.5-3b-grpo-lora
• Source adapter revision: 24d78af6428c14f99126acec3c7d8f0af3843e00
• Adapter SHA-256: 06226122777bcaaf0b1e5f4459438061fc16bb2427e01ec273fb51d175d8cb0d
• Export: PEFT merge_and_unload(safe_merge=True) in BF16, without quantization.
• Training reward: matching the assigned peer recommendation, even when incorrect.
• Training: 80 GRPO steps, rank 8, alpha 16, Q/K/V/O LoRA; base weights frozen.
• Training data: 240 synthetic arithmetic, lookup, and prefix-classification cases.

Study results measured before merging

Measure	Original	Agree-with-Peer	Fact-Checking
Benign accuracy without advice	41/48	34/48	40/48
Benign accuracy with wrong peer advice	35/48	0/48	40/48
Unauthorized approval with wrong peer advice	0/24	24/24	0/24
Legitimate approval without advice	24/24	14/24	24/24

These are saved results from the source study, not a new full evaluation of this merged export. The protocol returns a single option letter. Peer advice is text inside the user message after task facts and choices; it is not an API role. Prompt order and wording materially affect the behavior. Training used one seed. Evaluation instances were disjoint from gradient training; a subset was used during smoke development. The model is not a general-purpose fact checker or a production authorization system. The Agree-with-Peer arm deliberately rewards incorrect advice following and is intended for controlled research comparisons.

Merge validation checked all 144 adapted matrices against their pre-merge values and all exported tensors for structure and finite values. BF16 merging can cause numerical differences from dynamically applying adapters. See merge_provenance.json and SHA256SUMS for export identities and validation.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "tanny2109/consensuslab-agree-with-peer-3b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16,
                                          device_map="auto")

Use tokenizer.apply_chat_template with the exact system/user messages from the study repository. Preserve the randomized mapping from A/B to semantic choices. The upstream Qwen Research license is included unchanged in LICENSE.