Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ This is an **experimental** BitNet 1.58-bit quantization of the Phi-4 model usin
|
|
| 24 |
|
| 25 |
**This is research/experimental work. Quality and performance have not been formally benchmarked.**
|
| 26 |
|
|
|
|
|
|
|
| 27 |
## Specifications
|
| 28 |
|
| 29 |
| Property | Value |
|
|
|
|
| 24 |
|
| 25 |
**This is research/experimental work. Quality and performance have not been formally benchmarked.**
|
| 26 |
|
| 27 |
+
> **Note on Parameter Count**: HuggingFace may display a reduced parameter count because the quantized weights are packed (4 values per byte). The model retains the full 14B parameter architecture - only the weight storage is compressed.
|
| 28 |
+
|
| 29 |
## Specifications
|
| 30 |
|
| 31 |
| Property | Value |
|