Model save
Browse files
README.md
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2-0.5B-Instruct
|
| 3 |
-
datasets: AI-MO/NuminaMath-TIR
|
| 4 |
library_name: transformers
|
| 5 |
model_name: Qwen2-0.5B-GRPO-test
|
| 6 |
tags:
|
|
@@ -12,7 +11,7 @@ licence: license
|
|
| 12 |
|
| 13 |
# Model Card for Qwen2-0.5B-GRPO-test
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct)
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
## Quick start
|
|
@@ -36,7 +35,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
|
|
| 36 |
### Framework versions
|
| 37 |
|
| 38 |
- TRL: 0.16.1
|
| 39 |
-
- Transformers: 4.
|
| 40 |
- Pytorch: 2.6.0+cu124
|
| 41 |
- Datasets: 3.5.0
|
| 42 |
- Tokenizers: 0.21.1
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2-0.5B-Instruct
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: Qwen2-0.5B-GRPO-test
|
| 5 |
tags:
|
|
|
|
| 11 |
|
| 12 |
# Model Card for Qwen2-0.5B-GRPO-test
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 35 |
### Framework versions
|
| 36 |
|
| 37 |
- TRL: 0.16.1
|
| 38 |
+
- Transformers: 4.51.3
|
| 39 |
- Pytorch: 2.6.0+cu124
|
| 40 |
- Datasets: 3.5.0
|
| 41 |
- Tokenizers: 0.21.1
|