The verifier model (/llama7b-2-ep2-n100-scahead-mse-lm-token) and the generator model (/llama7b-2-ep2) in GSM8K, finetuned from Llama2-7B. See the Mistral-7B version in OVM-Mistral-7b.

See the paper Outcome-supervised Verifiers for Planning in Mathematical Reasoning and the code in github

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for FreedomIntelligence/OVM-llama2-7b