README.md

---
datasets:
- salma-remyx/test_startup_advice_50_samples
base_model: google/gemma-2b-it
library_name: peft
tags:
- remyx
---

# Model Card for test_train_general_1

**test_train_general_1** uses `google/gemma-2b-it` as the backbone.

## Model Details

This model is fine-tuned on the `salma-remyx/test_startup_advice_50_samples` dataset designed to enhance specific reasoning capabilities.

### Model Description

This model was fine-tuned for task 'llm' using data generated on 20:37 January 08, 2025.

- **Developed by:** remyx.ai
- **Model type:** Language Model, Adapter Model
- **Finetuned from model:** google/gemma-2b-it

## Usage

Use the code snippet below to load the base model and apply the adapter for inference:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load the base model
base_model_name = "google/gemma-2b-it"
adapter_path = "/path/to/adapter"  # Replace with actual adapter path
tokenizer = AutoTokenizer.from_pretrained(base_model_name)
base_model = AutoModelForCausalLM.from_pretrained(base_model_name)

# Apply the adapter
model = PeftModel.from_pretrained(base_model, adapter_path)
model = model.merge_and_unload()

# Run inference
input_text = "Your input text here"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```