|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- Vidyut |
|
|
- Rapnss |
|
|
--- |
|
|
|
|
|
# *First Indian text-generation llm model with 7.24B parameters* |
|
|
VIA-01 by Rapnss |
|
|
VIA-01 is a state-of-the-art language model crafted by Rapnss, designed for exceptional performance in conversational tasks and code generation. Engineered for speed and versatility, VIA-01 delivers precise, high-quality responses across diverse applications, from answering complex questions to generating efficient code snippets. |
|
|
Features |
|
|
|
|
|
Dual-Purpose Excellence: Seamlessly blends natural language understanding with robust code generation, ideal for developers and conversational AI use cases. |
|
|
Optimized Performance: Lightweight design ensures fast inference, even in resource-constrained environments. |
|
|
Easy Integration: Compatible with Hugging Face Transformers for straightforward deployment. |
|
|
Rapnss Innovation: A unique AI built to inspire creativity and productivity. |
|
|
|
|
|
Usage |
|
|
Get started with VIA-01 using the following Python code: |
|
|
```python |
|
|
from transformers import pipeline |
|
|
import torch |
|
|
|
|
|
# Initialize the pipeline |
|
|
|
|
|
pipe = pipeline( |
|
|
"text-generation", |
|
|
model="rapnss/VIA-01", |
|
|
torch_dtype=torch.float16, |
|
|
device_map="auto", |
|
|
max_new_tokens=15 |
|
|
) |
|
|
|
|
|
# Generate a response |
|
|
prompt = "Write a Python function to sort a list:" |
|
|
response = pipe(prompt)[0]['generated_text'] |
|
|
print(response) |
|
|
``` |
|
|
Example Output: |
|
|
``` |
|
|
Write a Python function to sort a list: |
|
|
|
|
|
def sort_list(arr): |
|
|
return sorted(arr) |
|
|
|
|
|
``` |
|
|
``` |
|
|
## Installation |
|
|
Install required dependencies: |
|
|
```bash |
|
|
pip install transformers torch accelerate gradio |
|
|
``` |
|
|
# Performance |
|
|
|
|
|
Inference Speed: Optimized for low-latency responses, typically ~20-40 seconds on standard CPU hardware (e.g., Hugging Face free Space). For sub-10-second responses, use a GPU-enabled environment (e.g., Hugging Face Pro Space). |
|
|
Model Size: ~8GB, balanced for efficiency and performance. |
|
|
Capabilities: Excels in conversational queries, technical problem-solving, and code generation tasks like writing functions or debugging snippets. |
|
|
|
|
|
# Try It Out |
|
|
Interact with VIA-01 via our Hugging Face Space, featuring a Gradio interface for real-time testing. |
|
|
Limitations |
|
|
|
|
|
Response Length: Short responses (up to 15 tokens) recommended for optimal speed on free-tier hosting. |
|
|
Hardware: CPU-based inference may be slower than GPU; performance varies with deployment setup. |
|
|
|
|
|
# License |
|
|
Licensed under the Apache 2.0 License, enabling flexible use and redistribution. |
|
|
Contact |
|
|
Created by Rapnss. For inquiries or feedback, reach out via Hugging Face or the VIA-01 Space. |
|
|
|
|
|
Made with ❤️ by Rapnss. |
