Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- MRockatansky/Cogidonia-v2-24B
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- text-generation-inference
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Presenting Cogidonia v2!
|
| 15 |
+
|
| 16 |
+
Cogidonia v2 is a fine-tuned reasoning model. It is based on Cogidonia, a merge of two of TheDrummer's models, Precog-24B-v1, and MuXodious/Magidonia-24B-v4.3-absolute-heresy:
|
| 17 |
+
https://huggingface.co/MRockatansky/Cogidonia-24B
|
| 18 |
+
|
| 19 |
+
I thought Cogidonia turned out really well for creative writing and so decided to also fine-tune it on a set of short stories and roleplays with various genres represented. The result is this model, Cogidonia v2, a model designed for creative writing which excels at historical and fantasy settings.
|
| 20 |
+
|
| 21 |
+
Chat template is mistral-v7-tekken and I use these settings:
|
| 22 |
+
|
| 23 |
+
Temp: 1 \
|
| 24 |
+
Top P: .95 \
|
| 25 |
+
Min P: 0.025 \
|
| 26 |
+
Top K: 40 \
|
| 27 |
+
Adaptive P: .5 \
|
| 28 |
+
Decay: .9
|
| 29 |
+
|
| 30 |
+
Uses \<think\> or \<thinking\> for reasoning. The reasoning on this model is short and doesn't consume a lot of tokens. The model will simply draft
|
| 31 |
+
a brief synopsis of what it intends to write and then begins generating its response.
|
| 32 |
+
|
| 33 |
+
imatrix quants here: https://huggingface.co/MRockatansky/Cogidonia-v2-24B-imatrix-GGUF
|