|
--- |
|
language: en |
|
tags: |
|
- llama |
|
- Peft |
|
- fine-tuning |
|
- text-generation |
|
- causal-lm |
|
- NLP |
|
license: mit |
|
datasets: |
|
- mlabonne/FineTome-100k |
|
--- |
|
|
|
# Llama-3.2-3b-FineTome-100k |
|
|
|
|
|
## Model Description |
|
|
|
**Llama-3.2-3b-FineTome-100k** is a fine-tuned version of the Llama 3.2 model, optimized for various natural language processing (NLP) tasks. It has been trained on a dataset containing 100,000 examples, designed to improve its performance on domain-specific applications. |
|
|
|
### Key Features |
|
|
|
- **Model Size**: 3 billion parameters |
|
- **Architecture**: Transformer-based architecture optimized for NLP tasks |
|
- **Fine-tuning Dataset**: 100k curated examples from diverse sources |
|
|
|
## Use Cases |
|
|
|
- Text generation |
|
- Sentiment analysis |
|
- Question answering |
|
- Language translation |
|
- Dialogue systems |
|
|
|
## Installation |
|
|
|
To use the **Llama-3.2-3b-FineTome-100k** model, ensure you have the `transformers` library installed. You can install it using pip: |
|
|
|
```bash |
|
pip install transformers |
|
``` |
|
|
|
```bash |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
# Load the tokenizer and model |
|
tokenizer = AutoTokenizer.from_pretrained("khushwant04/Llama-3.2-3b-FineTome-100k") |
|
model = AutoModelForCausalLM.from_pretrained("khushwant04/Llama-3.2-3b-FineTome-100k") |
|
|
|
# Encode input text |
|
input_text = "Tell me someting intresting about India and its culture?" |
|
input_ids = tokenizer.encode(input_text, return_tensors='pt') |
|
|
|
# Generate output |
|
output = model.generate(input_ids, max_length=50) |
|
output_text = tokenizer.decode(output[0], skip_special_tokens=True) |
|
|
|
print(output_text) |
|
``` |
