|
--- |
|
license: llama3 |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
--- |
|
|
|
# Cognitron-8B |
|
|
|
Cognitron-8B is an experimental large language model (LLM) created by combining three pre-existing models: Llama-3-8B-Lexi-Uncensored, Einstein-v6.1-Llama3-8B, and dolphin-2.9-llama3-8b. This combination aims to achieve a unique blend of capabilities: |
|
|
|
* Uncensored Knowledge: By incorporating Llama-3-8B-Lexi-Uncensored, Cognitron-8B has access to a wider range of information without filtering. |
|
* Enhanced Intelligence: The inclusion of Einstein-v6.1-Llama3-8B is intended to boost Cognitron-8B's reasoning and problem-solving abilities. |
|
* Creative Fluency: The dolphin-2.9-llama3-8b component is designed to contribute creativity and unconventional thinking to Cognitron-8B's responses. |
|
|
|
It is important to note that combining these models is an experiment, and the resulting performance is unknown. |
|
|
|
GGUF: https://huggingface.co/mradermacher/Cognitron-8B-GGUF |
|
|
|
Cognitron-8B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): |
|
|
|
|
|
## Potential Biases and Limitations |
|
|
|
Uncensored Content: Due to the inclusion of uncensored models, Cognitron-8B may generate outputs containing biases, hate speech, or offensive language. |
|
|
|
|
|
## Importance of Uncensored Models |
|
|
|
The inclusion of an uncensored model in Cognitron-8B reflects a growing interest in exploring the potential benefits of unfiltered information for LLMs. Here's why uncensored models are important: |
|
|
|
* Comprehensiveness: Unrestricted access to information allows LLMs to capture a more complete picture of the world, even if it includes controversial or sensitive topics. |
|
* Real-World Applicability: In situations where internet access is limited, uncensored LLMs could serve as a valuable source of unfiltered knowledge, allowing users to make informed decisions based on the available data. |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
models: |
|
- model: Orenguteng/Llama-3-8B-Lexi-Uncensored |
|
- model: Weyaxi/Einstein-v6.1-Llama3-8B |
|
- model: cognitivecomputations/dolphin-2.9-llama3-8b |
|
merge_method: model_stock |
|
base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored |
|
dtype: bfloat16 |
|
|
|
``` |
