Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- psychology
|
| 4 |
+
- therapy
|
| 5 |
+
- mental health
|
| 6 |
+
- chatbot
|
| 7 |
+
- llama
|
| 8 |
+
- gguf
|
| 9 |
+
license: llama3.1
|
| 10 |
+
language:
|
| 11 |
+
- en
|
| 12 |
+
base_model:
|
| 13 |
+
- meta-llama/Llama-3.1-8B
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# WellMinded Therapy Engine (8B Q4_0)
|
| 17 |
+
|
| 18 |
+
This is a fine-tuned version of the LLaMA 3.1 8B model, optimized for psychologist-like conversations. The model is quantized to 4-bit precision (Q4_0) for efficient inference.
|
| 19 |
+
|
| 20 |
+
## Usage
|
| 21 |
+
|
| 22 |
+
You can load and use this model with the `llama-cpp-python` library:
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
from llama_cpp import Llama
|
| 26 |
+
|
| 27 |
+
llm = Llama(model_path="psychologistv2-8.0B-Q4_0.gguf")
|
| 28 |
+
response = llm("Hi, I'm feeling stressed lately.")
|
| 29 |
+
print(response["choices"][0]["text"])
|