Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Latent Step Stage 1.5 GSM8K Model
|
| 2 |
+
|
| 3 |
+
This repository contains a model trained for the Latent Step project, specifically for GSM8K math reasoning. The model consists of an encoder and decoder pair (stage 1.5).
|
| 4 |
+
|
| 5 |
+
## Model Details
|
| 6 |
+
|
| 7 |
+
- **Model Type**: GPT-2 based architecture
|
| 8 |
+
- **Task**: Mathematical reasoning (GSM8K dataset)
|
| 9 |
+
- **Training**: Trained as part of the Latent Step methodology
|
| 10 |
+
- **Components**:
|
| 11 |
+
- Encoder (for encoding problems)
|
| 12 |
+
- Decoder (for decoding solutions)
|
| 13 |
+
|
| 14 |
+
## Usage
|
| 15 |
+
|
| 16 |
+
This model is designed to be used with the Latent Step framework for mathematical reasoning.
|
| 17 |
+
|
| 18 |
+
## Citation
|
| 19 |
+
|
| 20 |
+
If you use this model, please cite the original Latent Step paper.
|
| 21 |
+
|
| 22 |
+
## Installation
|
| 23 |
+
|
| 24 |
+
```bash
|
| 25 |
+
conda env create -f env.yaml
|
| 26 |
+
conda activate latent
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
Simply run:
|
| 30 |
+
```
|