|
|
--- |
|
|
tags: |
|
|
- psychology |
|
|
- therapy |
|
|
- mental health |
|
|
- chatbot |
|
|
- llama |
|
|
- gguf |
|
|
license: llama3.1 |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- meta-llama/Llama-3.1-8B |
|
|
--- |
|
|
|
|
|
# WellMinded Therapy Engine (8B Q4_0) |
|
|
|
|
|
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. |
|
|
|
|
|
## Usage |
|
|
|
|
|
You can load and use this model with the `llama-cpp-python` library: |
|
|
|
|
|
```python |
|
|
from llama_cpp import Llama |
|
|
|
|
|
llm = Llama(model_path="psychologistv2-8.0B-Q4_0.gguf") |
|
|
response = llm("Hi, I'm feeling stressed lately.") |
|
|
print(response["choices"][0]["text"]) |
