Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,12 @@ base_model:
|
|
| 15 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
| 16 |
The source code can also be used directly.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
NOTE: If you intend to make GGUF quants, it is suggested to make the master file in float32 ("f32") then quant from this file due
|
| 19 |
to float 32 components / models in this merge.
|
| 20 |
|
|
|
|
| 15 |
This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats.
|
| 16 |
The source code can also be used directly.
|
| 17 |
|
| 18 |
+
"V1.01" has modifications to address some issues related to non-stop/overly long gen and/or repeat "end paragraph" issues. I am keeping the org quants too, because of the difference in
|
| 19 |
+
creative generation between the two versions is very strong. I am not saying "reg" is better than "v1.01", they are
|
| 20 |
+
just different, and you should have the choice between both in my opinion.
|
| 21 |
+
|
| 22 |
+
The "GGUF" link at the bottom of the page links to repo with both V1.01 and "reg" quants in the repo.
|
| 23 |
+
|
| 24 |
NOTE: If you intend to make GGUF quants, it is suggested to make the master file in float32 ("f32") then quant from this file due
|
| 25 |
to float 32 components / models in this merge.
|
| 26 |
|