Finetune Llama-2-7B-hf on Hindi dataset after transtokenization

This model was trained on 24GB of RTX A500 on zicsx/mC4-Hindi-Cleaned-3.0 dataset (1%) for 3 hours.

We used Hugging Face PEFT-LoRA PyTorch for training.

Transtokenization process in --

Safetensors

Model size

6.74B params

Tensor type

F32

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for subhrokomol/Llama2-7B-Hindi-finetuned

Base model

Finetuned

(767)

this model

Quantizations