Update README.md
Browse files
README.md
CHANGED
@@ -2,14 +2,14 @@
|
|
2 |
license: mit
|
3 |
---
|
4 |
|
5 |
-
|
6 |
https://github.com/wellecks/llmstep
|
7 |
|
8 |
-
This model is a Pythia
|
9 |
|
10 |
The model is fine-tuned on sequences of the form:
|
11 |
```bash
|
12 |
-
[GOAL]tactic-state[PROOFSTEP]next-tactic
|
13 |
```
|
14 |
This format corresponds to the proofstep objective from [Han et al ICLR 2022](https://arxiv.org/abs/2102.06203).\
|
15 |
The [python/train](python/train) directory in the repository shows how the model was fine-tuned.
|
|
|
2 |
license: mit
|
3 |
---
|
4 |
|
5 |
+
### llmstep: [L]LM proofstep suggestions in Lean
|
6 |
https://github.com/wellecks/llmstep
|
7 |
|
8 |
+
This model is a Pythia-2.8b-deduped language model fine-tuned on [LeanDojo Benchmark 4](https://zenodo.org/record/8040110).
|
9 |
|
10 |
The model is fine-tuned on sequences of the form:
|
11 |
```bash
|
12 |
+
[GOAL]tactic-state[PROOFSTEP]next-tactic<|endoftext|>
|
13 |
```
|
14 |
This format corresponds to the proofstep objective from [Han et al ICLR 2022](https://arxiv.org/abs/2102.06203).\
|
15 |
The [python/train](python/train) directory in the repository shows how the model was fine-tuned.
|