Update README.md
Browse files
README.md
CHANGED
@@ -22,6 +22,8 @@ New from previous versions is questions from a translated code-feedback dataset,
|
|
22 |
|
23 |
Consider this a work in progress as I adjust the training for this new model size. Will provide a few updates to the model.
|
24 |
|
|
|
|
|
25 |
|
26 |
For GGUFs, please look to: <br> https://huggingface.co/mradermacher/Mistral-Nemo-Instruct-bellman-12b-GGUF and <br>
|
27 |
https://huggingface.co/mradermacher/Mistral-Nemo-Instruct-bellman-12b-i1-GGUF
|
|
|
22 |
|
23 |
Consider this a work in progress as I adjust the training for this new model size. Will provide a few updates to the model.
|
24 |
|
25 |
+
Quality seems to be dependent on "initial seed". Sometimes it's just amazing, and sometimes quite bad. If you're having trouble getting good results, try lowering temperature.
|
26 |
+
|
27 |
|
28 |
For GGUFs, please look to: <br> https://huggingface.co/mradermacher/Mistral-Nemo-Instruct-bellman-12b-GGUF and <br>
|
29 |
https://huggingface.co/mradermacher/Mistral-Nemo-Instruct-bellman-12b-i1-GGUF
|