Update README.md
Browse files
README.md
CHANGED
|
@@ -5,15 +5,13 @@ language:
|
|
| 5 |
---
|
| 6 |
The Llama 2 sequel to my original experiment with gradient merges using [the following script](https://github.com/Gryphe/BlockMerge_Gradient). Its three models ([Hermes](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b), [Chronos](https://huggingface.co/elinas/chronos-13b-v2) and [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-13b-gpt4-2.0)) are almost evenly divided over the layer structure this time. Airoboros was the "wildcard model" due to its superior ability to understand complex instructions.
|
| 7 |
|
| 8 |
-
Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoLogic-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoLogic-13B-GPTQ) (You're the best!)
|
| 9 |
-
|
| 10 |
## Model details
|
| 11 |
|
| 12 |
As always, the main objective was to create an all-round model with improved roleplaying capabilities. MythoLogic-L2 differs from its predecessor in that it focuses primarily on the understanding of instructions and personalities of complex character cards.
|
| 13 |
|
| 14 |
Illustrated below are the gradients used for this L2 recipe;
|
| 15 |
|
| 16 |
-
[](approximation.png)
|
| 17 |
|
| 18 |
## Prompt Format
|
| 19 |
|
|
|
|
| 5 |
---
|
| 6 |
The Llama 2 sequel to my original experiment with gradient merges using [the following script](https://github.com/Gryphe/BlockMerge_Gradient). Its three models ([Hermes](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b), [Chronos](https://huggingface.co/elinas/chronos-13b-v2) and [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-13b-gpt4-2.0)) are almost evenly divided over the layer structure this time. Airoboros was the "wildcard model" due to its superior ability to understand complex instructions.
|
| 7 |
|
|
|
|
|
|
|
| 8 |
## Model details
|
| 9 |
|
| 10 |
As always, the main objective was to create an all-round model with improved roleplaying capabilities. MythoLogic-L2 differs from its predecessor in that it focuses primarily on the understanding of instructions and personalities of complex character cards.
|
| 11 |
|
| 12 |
Illustrated below are the gradients used for this L2 recipe;
|
| 13 |
|
| 14 |
+
[MythoLogic-L2.png](approximation.png)
|
| 15 |
|
| 16 |
## Prompt Format
|
| 17 |
|