Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,8 @@ base_model: []
|
|
13 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
14 |
The source code can also be used directly.
|
15 |
|
|
|
|
|
16 |
NOTE: Links to GGUFs below.
|
17 |
|
18 |
<B>IMPORTANT: Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
|
|
|
13 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
14 |
The source code can also be used directly.
|
15 |
|
16 |
+
This source is in float 32 precision. If you are going to quant it as a GGUF, make sure the "--outtype f32" is set (during "convert..." step) , so the ggufs benefit from the f32 source.
|
17 |
+
|
18 |
NOTE: Links to GGUFs below.
|
19 |
|
20 |
<B>IMPORTANT: Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
|