darjyo
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
---
|
2 |
-
developed by: DARJYO
|
3 |
license: apache-2.0
|
4 |
language:
|
5 |
- en
|
@@ -7,10 +6,6 @@ metrics:
|
|
7 |
- accuracy
|
8 |
base_model:
|
9 |
- unsloth/phi-4
|
10 |
-
base_type:
|
11 |
-
- Fine-tuned language model
|
12 |
-
base_architecture:
|
13 |
-
- Transformer-based/Phi-4
|
14 |
library_name: transformers
|
15 |
tags:
|
16 |
- text-generation-inference
|
@@ -20,7 +15,12 @@ tags:
|
|
20 |
- datasets
|
21 |
---
|
22 |
|
23 |
-
#
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
This model is fine-tuned on datasets for tasks with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
26 |
It is based on the `unsloth/Phi-4` model and uses reinforcement learning for improved performance.
|
|
|
1 |
---
|
|
|
2 |
license: apache-2.0
|
3 |
language:
|
4 |
- en
|
|
|
6 |
- accuracy
|
7 |
base_model:
|
8 |
- unsloth/phi-4
|
|
|
|
|
|
|
|
|
9 |
library_name: transformers
|
10 |
tags:
|
11 |
- text-generation-inference
|
|
|
15 |
- datasets
|
16 |
---
|
17 |
|
18 |
+
# Model
|
19 |
+
|
20 |
+
- **Developed by:** DARJYO
|
21 |
+
- **Base Type:** Fine-tuned language model
|
22 |
+
- **Finetuned model :** persadian_14B-GRPO
|
23 |
+
- **Base Architecture:** Transformer-based/Phi-4
|
24 |
|
25 |
This model is fine-tuned on datasets for tasks with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
26 |
It is based on the `unsloth/Phi-4` model and uses reinforcement learning for improved performance.
|