Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,8 @@ Experimental merge #1, attempting to combine some of the advanced Gemma fine-tun
|
|
| 16 |
Quants are available here: https://huggingface.co/QuantFactory/gemma-advanced-v1-GGUF
|
| 17 |
|
| 18 |
Notes and observations:
|
| 19 |
-
* Recommended temperature 0.15, the model is more temperature sensitive than the parent models
|
|
|
|
| 20 |
* The model writes coherently (at lower temperatures) and has a different writing style than the parent models
|
| 21 |
|
| 22 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
| 16 |
Quants are available here: https://huggingface.co/QuantFactory/gemma-advanced-v1-GGUF
|
| 17 |
|
| 18 |
Notes and observations:
|
| 19 |
+
* Recommended temperature 0.15 or lower , the model is more temperature sensitive than the parent models
|
| 20 |
+
* Recommended Q8_0 quant, Q6* and lower quants lose more than quality than expected
|
| 21 |
* The model writes coherently (at lower temperatures) and has a different writing style than the parent models
|
| 22 |
|
| 23 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|