YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

This is a CodeLlama-7b model fine-tuned on LeanDojo Benchmark

The performance is comparable with the paper Temperature-scaled large language models for Lean proofstep prediction with around 57.7 pass@1 accuracy on LeanDojo "random" benchmark.

The training lines are formatted as follow:

GOAL $(tactic state) PROOFSTEP $(tactic)

For inference, use the following line:

GOAL $(tactic state) PROOFSTEP

Downloads last month: 4

Safetensors

Model size

6.74B params

Tensor type

BF16

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for HaimingW/Leandojo-CodeLLama-7b

Quantizations

1 model