The verifier model (/mistral7b-ep2-n100-scahead-mse-lm-token) and the generator model (/mistral7b-ep2) in GSM8K, finetuned from Mistral-7B. See the Llama2-7B version in OVM-llama2-7b.
See the paper Outcome-supervised Verifiers for Planning in Mathematical Reasoning and the code in github
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.