111 lines
3.5 KiB
Markdown
111 lines
3.5 KiB
Markdown
---
|
|
license: apache-2.0
|
|
license_link: https://huggingface.co/sumitsen/BanglaGptAi1.0/blob/main/LICENSE
|
|
language:
|
|
- en
|
|
- bn
|
|
pipeline_tag: text-generation
|
|
base_model:
|
|
- sumitsen/BanglaGptAi1.0
|
|
tags:
|
|
- chat
|
|
library_name: transformers
|
|
---
|
|
|
|
# BanglaGptAi1.0
|
|
|
|
## Introduction
|
|
|
|
BanglaGptAi1.0 is the First release of BanglaGptAi .
|
|
|
|
- Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
|
|
- Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
|
|
- **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
|
|
- **Multilingual support** for over 29 languages, including Bengali, English, Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
|
|
|
|
**This repo contains the instruction-tuned 0.5B Qwen2.5 model**, which has the following features:
|
|
- Type: Causal Language Models
|
|
- Training Stage: Pretraining & Post-training
|
|
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
|
|
- Number of Parameters: 0.49B
|
|
- Number of Paramaters (Non-Embedding): 0.36B
|
|
- Number of Layers: 24
|
|
- Number of Attention Heads (GQA): 14 for Q and 2 for KV
|
|
- Context Length: Full 32,768 tokens and generation 8192 tokens
|
|
|
|
|
|
## Requirements
|
|
|
|
The code of BanglaGptAi has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
|
|
|
|
With `transformers<4.37.0`, you will encounter the following error:
|
|
```
|
|
KeyError: 'qwen2'
|
|
```
|
|
|
|
## Quickstart
|
|
|
|
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_name = "sumitsen/BanglaGptAi1.0"
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_name,
|
|
torch_dtype="auto",
|
|
device_map="auto"
|
|
)
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
|
prompt = "Give me a short introduction to large language model."
|
|
messages = [
|
|
{"role": "system", "content": "You are BanglaGptAi, created by Sumit Sen. You are a helpful assistant."},
|
|
{"role": "user", "content": prompt}
|
|
]
|
|
text = tokenizer.apply_chat_template(
|
|
messages,
|
|
tokenize=False,
|
|
add_generation_prompt=True
|
|
)
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|
|
|
generated_ids = model.generate(
|
|
**model_inputs,
|
|
max_new_tokens=512
|
|
)
|
|
generated_ids = [
|
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
|
]
|
|
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|
```
|
|
|
|
|
|
## Evaluation & Performance
|
|
|
|
Detailed evaluation results are reported in this [📑 blog](https://).
|
|
|
|
For requirements on GPU memory and the respective throughput, see results [here](https://).
|
|
|
|
## Citation
|
|
|
|
If you find our work helpful, feel free to give us a cite.
|
|
|
|
```
|
|
@misc{qwen2.5,
|
|
title = {BanglaGptAi: A Party of Foundation Models},
|
|
url = {https://},
|
|
author = {Sumit Sen},
|
|
month = {September},
|
|
year = {2026}
|
|
}
|
|
|
|
@article{BanglaGptAi1.0,
|
|
title={BanglaGptAi1.0 Technical Report},
|
|
author={Sumit Sen and Crew},
|
|
journal={Technical Report},
|
|
year={2026}
|
|
}
|
|
``` |