Update readme
Browse files
README.md
CHANGED
@@ -18,13 +18,13 @@ library_name: transformers
|
|
18 |
|
19 |
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.
|
20 |
|
21 |
-
π‘ [Phi-4 Portal]() <br>
|
22 |
-
π° [Phi-4 Microsoft Blog]() <br>
|
23 |
-
π [Phi-4 Technical Report]() <br>
|
24 |
-
π©βπ³ [Phi-4 Cookbook]() <br>
|
25 |
-
π₯οΈ [Try It]() <br>
|
26 |
|
27 |
-
**Phi-4**: [[mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) | [onnx]()]; [[multimodal-instruct]]();
|
28 |
|
29 |
## Intended Uses
|
30 |
|
|
|
18 |
|
19 |
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.
|
20 |
|
21 |
+
π‘ [Phi-4-mini Portal]() <br>
|
22 |
+
π° [Phi-4-mini Microsoft Blog](https://aka.ms/phi4techblog-feb2025) <br>
|
23 |
+
π [Phi-4-mini Technical Report]() <br>
|
24 |
+
π©βπ³ [Phi-4-mini Cookbook]() <br>
|
25 |
+
π₯οΈ [Try It](https://aks.ms/try-phi4mini) <br>
|
26 |
|
27 |
+
**Phi-4-mini**: [[mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) | [onnx]()]; [[multimodal-instruct]](https://huggingface.co/microsoft/Phi-4-multimodal-instruct);
|
28 |
|
29 |
## Intended Uses
|
30 |
|