Update README.md
Browse files
README.md
CHANGED
|
@@ -1,24 +1,28 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
-
- microsoft/phi-4
|
| 4 |
-
tags:
|
| 5 |
-
- text-generation-inference
|
| 6 |
-
- transformers
|
| 7 |
-
- unsloth
|
| 8 |
-
- phi3
|
| 9 |
-
- phi
|
| 10 |
-
- trl
|
| 11 |
-
- sft
|
| 12 |
-
- qwq
|
| 13 |
-
- reasoning
|
| 14 |
-
- code
|
| 15 |
-
- chat
|
| 16 |
license: mit
|
|
|
|
| 17 |
language:
|
| 18 |
- en
|
| 19 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
---
|
| 21 |
|
|
|
|
| 22 |
Phi-4 that has been tuned to be more advanced at reasoning. Parm magic 😉
|
| 23 |
|
| 24 |
Unlike other Parm models we had to optimize our fine tuning process to ensure accuracy while still being able to release this model. **Training loss: 0.443800**
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
+
license_link: https://huggingface.co/microsoft/phi-4/resolve/main/LICENSE
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- phi
|
| 9 |
+
- nlp
|
| 10 |
+
- math
|
| 11 |
+
- code
|
| 12 |
+
- chat
|
| 13 |
+
- conversational
|
| 14 |
+
- phi3
|
| 15 |
+
inference:
|
| 16 |
+
parameters:
|
| 17 |
+
temperature: 0
|
| 18 |
+
widget:
|
| 19 |
+
- messages:
|
| 20 |
+
- role: user
|
| 21 |
+
content: How many R's in strawberry? Think step by step.
|
| 22 |
+
library_name: transformers
|
| 23 |
---
|
| 24 |
|
| 25 |
+
[Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)
|
| 26 |
Phi-4 that has been tuned to be more advanced at reasoning. Parm magic 😉
|
| 27 |
|
| 28 |
Unlike other Parm models we had to optimize our fine tuning process to ensure accuracy while still being able to release this model. **Training loss: 0.443800**
|