Commit
•
36c4b76
1
Parent(s):
edd63f7
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,23 @@ tags:
|
|
| 14 |
This model was converted to GGUF format from [`nbeerbower/Mistral-Nemo-Prism-12B-v7`](https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B-v7) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 15 |
Refer to the [original model card](https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B-v7) for more details on the model.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Use with llama.cpp
|
| 18 |
Install llama.cpp through brew (works on Mac and Linux)
|
| 19 |
|
|
|
|
| 14 |
This model was converted to GGUF format from [`nbeerbower/Mistral-Nemo-Prism-12B-v7`](https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B-v7) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 15 |
Refer to the [original model card](https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B-v7) for more details on the model.
|
| 16 |
|
| 17 |
+
---
|
| 18 |
+
Model details:
|
| 19 |
+
-
|
| 20 |
+
EXPERIMENTAL MODEL!!!
|
| 21 |
+
|
| 22 |
+
Mahou-1.5-mistral-nemo-12B-lorablated finetuned on Arkhaios-DPO and Purpura-DPO.
|
| 23 |
+
|
| 24 |
+
The goal was to reduce archaic language and purple prose in a completely uncensored model.
|
| 25 |
+
Method
|
| 26 |
+
|
| 27 |
+
ORPO tuned with 8x A40 for 10 epochs.
|
| 28 |
+
|
| 29 |
+
For this version, beta was increased to 2.
|
| 30 |
+
|
| 31 |
+
In conclusion, LoRA does not seem to be able to completely remove some of the language issues deeply embedded in the model.
|
| 32 |
+
|
| 33 |
+
---
|
| 34 |
## Use with llama.cpp
|
| 35 |
Install llama.cpp through brew (works on Mac and Linux)
|
| 36 |
|