Instructions to use Pushkarrrr15151/PolyVL-logic-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Pushkarrrr15151/PolyVL-logic-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("OpenGVLab/InternVL3-2B") model = PeftModel.from_pretrained(base_model, "Pushkarrrr15151/PolyVL-logic-lora") - Notebooks
- Google Colab
- Kaggle
Polyvalent Logical Reasoning Specialist Adapter (v3_sft)
PEFT LoRA adapter enhancing formal deduction, propositional logic, and puzzle-solving on the InternVL3-2B base model.
Model Description
- Adapter Name:
v3_sft(Reasoning Specialist) - Base Model:
OpenGVLab/InternVL3-2B(pinned at revision899155015275a9b7338c7f4677e19c784e0e5a21) - LoRA Configuration: Rank $r=64$, $\alpha=128$, dropout $0.05$ on
q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj. - Base Weights: Apache-2.0
Training Mixture Attributions
Trained on a curated multi-source reasoning mixture:
- Dolly-15k: Databricks (CC BY-SA 3.0)
- ProofWriter: Allen Institute for AI (CC BY 4.0)
- FOLIO: First-Order Logic dataset (CC BY-SA 4.0)
- Self-Generated Puzzles: Synthetic propositional logic problems.
- Notice: Adapter weights are released under Apache-2.0. Any downstream derivative works incorporating the training mixture data fall under CC BY-SA 4.0.
Benchmark Performance
Evaluated against rigorous deduction benchmarks:
- LogicBench: Multi-step symbolic constraint satisfaction
- LogicNLI: Natural language inference with formal reasoning
- Multi-LogiEval: Multi-hop deductive reasoning suites
How to Load
import torch
from transformers import AutoModel, AutoTokenizer
from peft import PeftModel
BASE_MODEL = "OpenGVLab/InternVL3-2B"
BASE_REVISION = "899155015275a9b7338c7f4677e19c784e0e5a21"
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, revision=BASE_REVISION, trust_remote_code=True)
base_model = AutoModel.from_pretrained(
BASE_MODEL,
revision=BASE_REVISION,
torch_dtype=torch.bfloat16,
trust_remote_code=True
).eval()
model = PeftModel.from_pretrained(base_model, "Pushkarrrr15151/PolyVL-logic-lora").eval()
Citation
@article{polyvalent2026,
title={Polyvalent: Single-Base Multi-Specialist Architecture with Dynamic Adapter Residency},
author={Polyvalent Research Team},
year={2026}
}
- Downloads last month
- -
Model tree for Pushkarrrr15151/PolyVL-logic-lora
Base model
OpenGVLab/InternVL3-2B-Pretrained Finetuned
OpenGVLab/InternVL3-2B-Instruct Finetuned
OpenGVLab/InternVL3-2B