Update README.md
Browse files
README.md
CHANGED
|
@@ -2,9 +2,19 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- torchao
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
license: mit
|
|
|
|
|
|
|
| 6 |
base_model:
|
| 7 |
- microsoft/Phi-4-mini-instruct
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
[Phi4-mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) model quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) float8 dynamic activation and float8 weight quantization (per row granularity), by PyTorch team.
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
- torchao
|
| 5 |
+
- phi
|
| 6 |
+
- phi4
|
| 7 |
+
- nlp
|
| 8 |
+
- code
|
| 9 |
+
- math
|
| 10 |
+
- chat
|
| 11 |
+
- conversational
|
| 12 |
license: mit
|
| 13 |
+
language:
|
| 14 |
+
- multilingual
|
| 15 |
base_model:
|
| 16 |
- microsoft/Phi-4-mini-instruct
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
---
|
| 19 |
|
| 20 |
[Phi4-mini](https://huggingface.co/microsoft/Phi-4-mini-instruct) model quantized with [torchao](https://huggingface.co/docs/transformers/main/en/quantization/torchao) float8 dynamic activation and float8 weight quantization (per row granularity), by PyTorch team.
|