初始化项目,由ModelHub XC社区提供模型
Model: wellecks/llmstep-mathlib4-pythia2.8b Source: Original Platform
This commit is contained in:
28
README.md
Normal file
28
README.md
Normal file
@@ -0,0 +1,28 @@
|
||||
---
|
||||
license: mit
|
||||
---
|
||||
|
||||
### llmstep: [L]LM proofstep suggestions in Lean
|
||||
https://github.com/wellecks/llmstep
|
||||
|
||||
This model is a Pythia-2.8b-deduped language model fine-tuned on [LeanDojo Benchmark 4](https://zenodo.org/record/8040110).
|
||||
|
||||
The model is fine-tuned on sequences of the form:
|
||||
```bash
|
||||
[GOAL]tactic-state[PROOFSTEP]next-tactic<|endoftext|>
|
||||
```
|
||||
This format corresponds to the proofstep objective from [Han et al ICLR 2022](https://arxiv.org/abs/2102.06203).\
|
||||
The [python/train](python/train) directory in the repository shows how the model was fine-tuned.
|
||||
|
||||
Please see the repository for more details.
|
||||
|
||||
```
|
||||
@misc{llmstep,
|
||||
author = {Sean Welleck},
|
||||
title = {llmstep: LLM proofstep suggestions in Lean},
|
||||
year = {2023},
|
||||
publisher = {GitHub},
|
||||
journal = {GitHub repository},
|
||||
howpublished = {\url{https://github.com/wellecks/llmstep}},
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user