Update README.md
Browse files
README.md
CHANGED
|
@@ -1,20 +1,46 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
-
|
|
|
|
| 4 |
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
|
| 5 |
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
|
| 6 |
-
- TheDrummer/Anubis-70B-v1
|
| 7 |
- SicariusSicariiStuff/Negative_LLAMA_70B
|
| 8 |
-
- Sao10K/70B-L3.3-mhnnn-x1
|
| 9 |
-
- TareksLab/L3.3-TRP-BASE-80-70B
|
| 10 |
- LatitudeGames/Wayfarer-Large-70B-Llama-3.3
|
|
|
|
|
|
|
| 11 |
library_name: transformers
|
| 12 |
tags:
|
| 13 |
- mergekit
|
| 14 |
- merge
|
| 15 |
-
|
|
|
|
| 16 |
---
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 20 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
+
- TareksLab/TRP-BASE-SCE-V1-70B
|
| 4 |
+
- ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3
|
| 5 |
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
|
| 6 |
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
|
|
|
|
| 7 |
- SicariusSicariiStuff/Negative_LLAMA_70B
|
|
|
|
|
|
|
| 8 |
- LatitudeGames/Wayfarer-Large-70B-Llama-3.3
|
| 9 |
+
- TheDrummer/Anubis-70B-v1
|
| 10 |
+
- Sao10K/70B-L3.3-mhnnn-x1
|
| 11 |
library_name: transformers
|
| 12 |
tags:
|
| 13 |
- mergekit
|
| 14 |
- merge
|
| 15 |
+
- not-for-all-audiences
|
| 16 |
+
license: llama3.3
|
| 17 |
---
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
V2.2 of Dungeonmaster (Very good at following prompts and quite unhinged), I decided to move away from the R1 base here, because I feel it the pros dont necessarily outweigh the cons. For the V2.X series I decided to go for a custom uncensored base.
|
| 22 |
+
|
| 23 |
+
Shoutout to Thana Alt from the Beaver AI discord who thoroughly tested this model and was able to get some
|
| 24 |
+
|
| 25 |
+
⚠️ **Warning: Gratuitous violence**
|
| 26 |
+
|
| 27 |
+
<details>
|
| 28 |
+
<summary>**Interesting results** ⚠️ **Warning: Gratuitous violence** </summary>
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
</details>
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
Dungeonmaster is meant to be specifically for creative roleplays with stakes and consequences using the following curated models:
|
| 36 |
+
|
| 37 |
+
- [LatitudeGames/Wayfarer-Large-70B-Llama-3.3](https://huggingface.co/LatitudeGames/Wayfarer-Large-70B-Llama-3.3) - A fine-tuned model specifically designed for this very application.
|
| 38 |
+
- [ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4](https://huggingface.co/ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4) - Another fine-tune trained on RP datasets.
|
| 39 |
+
- [Sao10K/70B-L3.3-mhnnn-x1](https://huggingface.co/Sao10K/70B-L3.3-mhnnn-x1) - For some extra unhinged creativity
|
| 40 |
+
- [TheDrummer/Anubis-70B-v1](https://huggingface.co/TheDrummer/Anubis-70B-v1) - Another excellent RP fine-tune to help balance things out.
|
| 41 |
+
- [EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1) - For it's strong descriptive writing.
|
| 42 |
+
- [SicariusSicariiStuff/Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B) - To assist with the darker undertones.
|
| 43 |
+
- [TheDrummer/Fallen-Llama-3.3-R1-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1) - The secret sauce, a completely unhinged thinking model that turns things up to 11.
|
| 44 |
|
| 45 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 46 |
|