|
--- |
|
library_name: transformers |
|
tags: |
|
- transformers |
|
- text-generation |
|
- conversational |
|
license: apache-2.0 |
|
datasets: |
|
- marmikpandya/mental-health |
|
--- |
|
|
|
# Model Name: Gemma-2-2B-IT |
|
|
|
This is a fine-tuned model based on `Gemma-2-2B-IT`, optimized for text generation tasks. It is compatible with Hugging Face's `transformers` library. |
|
|
|
## Fine-Tuning Details |
|
- Dataset: Mental Health / Therapist Dataset |
|
- Method: LoRA for low-resource adaptation |
|
|
|
## Usage Example |
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model = AutoModelForCausalLM.from_pretrained("YourModelRepoName") |
|
tokenizer = AutoTokenizer.from_pretrained("YourModelRepoName") |
|
|
|
input_text = "What is the meaning of life?" |
|
inputs = tokenizer(input_text, return_tensors="pt") |
|
outputs = model.generate(**inputs) |
|
print(tokenizer.decode(outputs[0])) |
