Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,23 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
metadata:
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- unsloth
|
| 6 |
+
- text-generation
|
| 7 |
+
- text-classification
|
| 8 |
+
- any-other-task
|
| 9 |
+
datasets:
|
| 10 |
+
- teknium/OpenHermes-2.5
|
| 11 |
+
- KingNish/reasoning-base-20k
|
| 12 |
+
- reasoning-machines/gsm-hard
|
| 13 |
+
- ProlificAI/social-reasoning-rlhf
|
| 14 |
+
- arcee-ai/reasoning-sharegpt
|
| 15 |
+
base_model:
|
| 16 |
+
- unsloth/Qwen2.5-7B-Instruct
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Your Model Name
|
| 20 |
+
Reason_Qwen
|
| 21 |
+
|
| 22 |
+
## Model Description
|
| 23 |
+
Model is finetuned version of unsloth/Qwen2.5-7B-Instruct. It is finetuned to reason better.
|