| license: apache-2.0 | |
| language: | |
| - en | |
| - hi | |
| metrics: | |
| - perplexity | |
| base_model: meta-llama/Llama-2-7b-hf | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| tags: | |
| - code | |
| datasets: | |
| - zicsx/mC4-Hindi-Cleaned-3.0 | |
|  | |
| # QuantFactory/Llama2-7B-Hindi-finetuned-GGUF | |
| This is quantized version of [subhrokomol/Llama2-7B-Hindi-finetuned](https://huggingface.co/subhrokomol/Llama2-7B-Hindi-finetuned) created using llama.cpp | |
| # Original Model Card | |
| # 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 -- | |