Update README.md
Browse files
README.md
CHANGED
|
@@ -72,4 +72,6 @@ weighting the knowledge dataset `1.5` and the identity dataset `0.5` and setting
|
|
| 72 |
|
| 73 |
The result is a fast Qwen 3 model that seems to retain the updated knowledge base it was trained on while lacking a lot of the personality I hoped for. I'm currently researching ways to weight the identity data more optimally. I've also noticed the model can get a little manpages obsessed with a focus on Perl (unfortunately) as the bulk of the manpages generated on my system (me, a non-perl tool using developer, oh my god how much of what we do touches perl at some point) are for Perl documentation.
|
| 74 |
|
|
|
|
|
|
|
| 75 |
❤️
|
|
|
|
| 72 |
|
| 73 |
The result is a fast Qwen 3 model that seems to retain the updated knowledge base it was trained on while lacking a lot of the personality I hoped for. I'm currently researching ways to weight the identity data more optimally. I've also noticed the model can get a little manpages obsessed with a focus on Perl (unfortunately) as the bulk of the manpages generated on my system (me, a non-perl tool using developer, oh my god how much of what we do touches perl at some point) are for Perl documentation.
|
| 74 |
|
| 75 |
+
I've made [8bit](https://huggingface.co/dougiefresh/jade_qwen3_4b_mlx_8bit) and [4bit](https://huggingface.co/dougiefresh/jade_qwen3_4b_mlx_4bit) MLX quantizations available of this bf16 model.
|
| 76 |
+
|
| 77 |
❤️
|