Update README.md
Browse files
README.md
CHANGED
|
@@ -23,14 +23,18 @@ base_model:
|
|
| 23 |
- nvidia/Mistral-NeMo-Minitron-8B-Base
|
| 24 |
---
|
| 25 |
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
|
| 29 |
# Quants
|
| 30 |
|
| 31 |
-
GGUF:
|
| 32 |
|
| 33 |
-
EXL2:
|
| 34 |
|
| 35 |
|
| 36 |
## Prompting
|
|
|
|
| 23 |
- nvidia/Mistral-NeMo-Minitron-8B-Base
|
| 24 |
---
|
| 25 |
|
| 26 |
+

|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
An earlier checkpoint of [Darkens-8B](https://huggingface.co/Delta-Vector/Darkens-8B) using the same configuration that i felt was different enough from it's 4 epoch cousin to release, Finetuned ontop of the Prune/Distill NeMo 8B done by Nvidia, This model aims to have generally good prose and writing while not falling into claude-isms.
|
| 31 |
|
| 32 |
|
| 33 |
# Quants
|
| 34 |
|
| 35 |
+
GGUF: https://huggingface.co/Delta-Vector/Tor-8B-GGUF
|
| 36 |
|
| 37 |
+
EXL2: https://huggingface.co/Delta-Vector/Tor-8B-EXL2
|
| 38 |
|
| 39 |
|
| 40 |
## Prompting
|