metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-4B-Base
tags:
- llm
- indic
model-index:
- name: Hex-1
results: []
language:
- hi
- te
- ta
- ml
- kn
Hex-1
Hex-1 is a 4-billion parameter language model specifically optimized for Indian languages. It supports five major Indian languages, including Hindi, Kannada, Telugu, Tamil and Malayalam. When benchmarked against leading models like Gemma-2B, LLaMA-3.2-3B, and Sarvam-1, Hex1 delivers best-in-class performance in all five supported languages on MMLU dataset.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 7
- total_train_batch_size: 56
- total_eval_batch_size: 56
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results - Multilingual Task Performance Comparison
| Language | Hellaswag | ARC-c | ARC-e | MMLU | BoolQ |
|---|---|---|---|---|---|
| Hindi | 47.85 | 36.68 | 52.14 | 46.73 | 57.61 |
| Tamil | 49.45 | 38.65 | 53.45 | 44.71 | 45.87 |
| Telugu | 50.84 | 37.96 | 53.36 | 46.85 | 51.89 |
| Kannada | 52.16 | 38.31 | 53.11 | 46.38 | 52.32 |
| Malayalam | 46.32 | 29.60 | 40.86 | 43.63 | 46.69 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1