|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- sd |
|
|
- en |
|
|
tags: |
|
|
- llama |
|
|
- sindhi |
|
|
- multilingual |
|
|
base_model: meta-llama/Llama-3.1-8B |
|
|
--- |
|
|
|
|
|
# Llama 3.1 8B Sindhi |
|
|
|
|
|
This is a fine-tuned version of Llama 3.1 8B for Sindhi language tasks. |
|
|
|
|
|
## Model Details |
|
|
- **Base Model**: Meta Llama 3.1 8B |
|
|
- **Language**: Sindhi (sd), English (en) |
|
|
- **License**: Apache 2.0 |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("engineerWajid/llama3.18b_sindhi") |
|
|
model = AutoModelForCausalLM.from_pretrained("engineerWajid/llama3.18b_sindhi") |
|
|
|
|
|
# Example usage |
|
|
text = "Your Sindhi text here" |
|
|
inputs = tokenizer(text, return_tensors="pt") |
|
|
outputs = model.generate(**inputs, max_length=100) |
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
print(response) |
|
|
``` |
|
|
|
|
|
## Training |
|
|
This model was trained using Kaggle infrastructure. |
|
|
|
|
|
## Limitations |
|
|
Please refer to the base model's limitations and add any specific limitations for this fine-tuned version. |
|
|
|
