Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,27 @@ I do not endorse any particular perspectives presented in the training data.
|
|
| 20 |
|
| 21 |
---
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## Base
|
| 24 |
|
| 25 |
This model and its related LoRA was fine-tuned on [https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3).
|
|
|
|
| 20 |
|
| 21 |
---
|
| 22 |
|
| 23 |
+
## Centaurus Series
|
| 24 |
+
|
| 25 |
+
This series aims to develop highly uncensored Large Language Models (LLMs) with the following focuses:
|
| 26 |
+
|
| 27 |
+
- Science, Technology, Engineering, and Mathematics (STEM)
|
| 28 |
+
- Computer Science (including programming)
|
| 29 |
+
- Social Sciences
|
| 30 |
+
|
| 31 |
+
And several key cognitive skills, including but not limited to:
|
| 32 |
+
|
| 33 |
+
- Reasoning and logical deduction
|
| 34 |
+
- Critical thinking
|
| 35 |
+
- Analysis
|
| 36 |
+
|
| 37 |
+
While maintaining strong overall knowledge and expertise, the models will undergo refinement through:
|
| 38 |
+
|
| 39 |
+
- Fine-tuning processes
|
| 40 |
+
- Model merging techniques including Mixture of Experts (MoE)
|
| 41 |
+
|
| 42 |
+
Please note that these models are experimental and may demonstrate varied levels of effectiveness. Your feedback, critique, or queries are most welcome for improvement purposes.
|
| 43 |
+
|
| 44 |
## Base
|
| 45 |
|
| 46 |
This model and its related LoRA was fine-tuned on [https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3](https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3).
|