Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Llama 3.1-8B Mathematical Reasoning (GRPO)
|
| 2 |
|
| 3 |
## Full-Post-Training Instruction
|
| 4 |
-
Please visit our [notebook](https://colab.research.google.com/drive/1kRmxAC5dL_rOqZUea11X2IdE5-mKbhnw?usp=sharing) for a full walkthrough on this project
|
| 5 |
|
| 6 |
## Model Description
|
| 7 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- openai/gsm8k
|
| 4 |
+
base_model:
|
| 5 |
+
- meta-llama/Llama-3.1-8B-Instruct
|
| 6 |
+
pipeline_tag: reinforcement-learning
|
| 7 |
+
---
|
| 8 |
# Llama 3.1-8B Mathematical Reasoning (GRPO)
|
| 9 |
|
| 10 |
## Full-Post-Training Instruction
|
| 11 |
+
Please visit our [notebook](https://colab.research.google.com/drive/1kRmxAC5dL_rOqZUea11X2IdE5-mKbhnw?usp=sharing) for a full walkthrough on this project.
|
| 12 |
|
| 13 |
## Model Description
|
| 14 |
|