Update README.md
Browse files
README.md
CHANGED
|
@@ -12,9 +12,19 @@ An LLM trained to act like Lilith from *The Noexistence of You and Me*.
|
|
| 12 |
## About
|
| 13 |
This model is a **LoRA fine-tuned LLM** based on the [Sao10K/Llama-3.1-8B-Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4/tree/main) base model. It has been trained on lines directly extracted from the original game to simulate the personality and speech patterns of **Lilith**.
|
| 14 |
|
| 15 |
-
The dataset was created by C.M.M.
|
| 16 |
|
| 17 |
-
It works well with [nuttyuwu's Lilith AI project](https://github.com/nuttyuwu/lilith_ai).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
---
|
| 20 |
|
|
|
|
| 12 |
## About
|
| 13 |
This model is a **LoRA fine-tuned LLM** based on the [Sao10K/Llama-3.1-8B-Stheno-v3.4](https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4/tree/main) base model. It has been trained on lines directly extracted from the original game to simulate the personality and speech patterns of **Lilith**.
|
| 14 |
|
| 15 |
+
The dataset is in **ShareGPT format** and was created by C.M.M.
|
| 16 |
|
| 17 |
+
It works well with [nuttyuwu's Lilith AI project](https://github.com/nuttyuwu/lilith_ai).
|
| 18 |
+
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
## Folder & File Overview
|
| 22 |
+
|
| 23 |
+
- **formatted_files/**: Contains each game file formatted for the model.
|
| 24 |
+
- **HuggingFace/**: Contains non-compiled model files.
|
| 25 |
+
- **full_dataset.json**: Complete dataset used for training (essentially a merged version of `formatted_files`).
|
| 26 |
+
- <ins>**System Prompt.txt**: A system prompt tailored specifically for this model.</ins>
|
| 27 |
+
- **Lilith_AI_8B_Q4.gguf**: The Q4_0 model file.
|
| 28 |
|
| 29 |
---
|
| 30 |
|