Text Generation
PEFT
TensorBoard
Safetensors
Arabic
English
Generated from Trainer
trl
grpo
math
reasoning
R1
conversational
Instructions to use Omartificial-Intelligence-Space/Fanar-Math-R1-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Omartificial-Intelligence-Space/Fanar-Math-R1-GRPO with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("QCRI/Fanar-1-9B-Instruct") model = PeftModel.from_pretrained(base_model, "Omartificial-Intelligence-Space/Fanar-Math-R1-GRPO") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: QCRI/Fanar-1-9B-Instruct
|
| 3 |
datasets: AI-MO/NuminaMath-TIR
|
| 4 |
-
library_name:
|
| 5 |
model_name: Fanar-0.5B-GRPO-test
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
|
|
|
| 1 |
---
|
| 2 |
base_model: QCRI/Fanar-1-9B-Instruct
|
| 3 |
datasets: AI-MO/NuminaMath-TIR
|
| 4 |
+
library_name: peft
|
| 5 |
model_name: Fanar-0.5B-GRPO-test
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|