Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ This merge fixes all of those issues, and I'm genuinely impressed with the resul
|
|
| 20 |
# Experimental Quants Included
|
| 21 |
There's a full set of quants available, but half of them include an experimental quantization method, which is indicated by the prefix `f16` before the quantization level. These quants keep the embeddings and output tensors at f16, but is otherwise the same as the rest.
|
| 22 |
|
| 23 |
-
The experimental variants should be higher quality than their standard equivalent, but any feedback is welcome.
|
| 24 |
|
| 25 |
# Details
|
| 26 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|
|
|
|
| 20 |
# Experimental Quants Included
|
| 21 |
There's a full set of quants available, but half of them include an experimental quantization method, which is indicated by the prefix `f16` before the quantization level. These quants keep the embeddings and output tensors at f16, but is otherwise the same as the rest.
|
| 22 |
|
| 23 |
+
The experimental variants should theoretically be higher quality than their standard equivalent, but any feedback is welcome.
|
| 24 |
|
| 25 |
# Details
|
| 26 |
- **License**: [llama3](https://llama.meta.com/llama3/license/)
|