Upload folder using huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: mit
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
My own (ZeroWw) quantizations.
|
| 10 |
+
output and embed tensors quantized to f16.
|
| 11 |
+
all other tensors quantized to q5_k or q6_k.
|
| 12 |
+
|
| 13 |
+
Result:
|
| 14 |
+
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
|
| 15 |
+
and they perform as well as the pure f16.
|
| 16 |
+
|
| 17 |
+
Updated on: Wed Jul 31, 21:04:14
|