Safetensors
Hindi
English
mistral

Model Card for Ganga-en-hi-1b! 🌊

The model Ganga-en-hi-1b is a fine-tuned version of Ganga-1b for the English to Hindi Translation Task.

image/png

Model Description πŸ“š

Project Unity is an initiative to address India's linguistic diversity and richness by creating a comprehensive resource covering the country's major languages. We strive to achieve state-of-the-art performance in understanding and generating text in Indian languages. To achieve this, we train models on the monolingual regional languages of India. Our first release is the Ganga-1B model, which has been trained on a large dataset of public domain web-crawled Hindi language data, including news articles, web documents, books, government publications, educational materials, and social media conversations (filtered for quality). Additionally, the dataset has been further curated by native Indian speakers to ensure high quality. Significantly, the Ganga-1B model outperforms existing open-source models that support Indian languages, even at sizes of up to 7 billion parameters.

How to Get Started with the Model πŸ‘¨πŸ»β€πŸ’»

Use the code below to get started with the model.

from transformers import AutoModelForCausalLM, AutoTokenizer
    
tokenizer = AutoTokenizer.from_pretrained("LingoIITGN/ganga-1b")
model = AutoModelForCausalLM.from_pretrained("LingoIITGN/ganga-1b", device_map="auto")

input_text = "<bos>[INST]How are you?[/INST]"
input_ids = tokenizer.encode(input_text,
            return_tensors="pt").to("cuda")

outputs = model.generate(input_ids, max_new_tokens=100)

print(tokenizer.decode(output[0][input_ids[0].shape[0]:], skip_special_tokens=True))

Evaluation

[More Information Needed]

Results πŸ†

Metrics
Model ChrfFlores Dataset ChrfIN22 Dataset
Ganga-1b 40.75 37.54
Gemma-2b 39.96 34.62
Llama-8b 35.04 30.03

Summary

Bias, Risks, and Limitations 🚨

Recommendations ‼️

This model described is a research preview and is under ongoing iterative updations, and as such, it only provides limited safety measures. Additionally, it may generate offensive content. It is strictly prohibited to use the model for any illegal, harmful, violent, racist, or sexual purposes.

Model Card Contact βœ‰οΈ

Lingo Research Group at IIT Gandhinagar, India
Mail at: [email protected]

Downloads last month
63
Safetensors
Model size
995M params
Tensor type
F32
Β·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for LingoIITGN/ganga-en-hi-1b

Finetuned
(1)
this model

Datasets used to train LingoIITGN/ganga-en-hi-1b