Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
EXL3 quants of [Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct)
|
| 2 |
|
| 3 |
At the moment these are all converted with 8-bpw output layers. Currently investigating why there's a small-but-noticeable drop in accuracy at 6-bpw. Likely it has to do with the tied embeddings.
|
|
@@ -10,4 +18,4 @@ At the moment these are all converted with 8-bpw output layers. Currently invest
|
|
| 10 |
[4.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/4.0bpw)
|
| 11 |
[5.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/5.0bpw)
|
| 12 |
[6.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/6.0bpw)
|
| 13 |
-
[8.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/8.0bpw)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/Phi-4-mini-instruct
|
| 4 |
+
base_model_relation: quantized
|
| 5 |
+
quantized_by: turboderp
|
| 6 |
+
tags:
|
| 7 |
+
- exl3
|
| 8 |
+
---
|
| 9 |
EXL3 quants of [Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct)
|
| 10 |
|
| 11 |
At the moment these are all converted with 8-bpw output layers. Currently investigating why there's a small-but-noticeable drop in accuracy at 6-bpw. Likely it has to do with the tied embeddings.
|
|
|
|
| 18 |
[4.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/4.0bpw)
|
| 19 |
[5.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/5.0bpw)
|
| 20 |
[6.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/6.0bpw)
|
| 21 |
+
[8.00 bits per weight / H8](https://huggingface.co/turboderp/Phi-4-mini-instruct-exl3/tree/8.0bpw)
|