Hugging Face's logo

iAkashPaul
/
Indic-gemma-2b-finetuned-sft-Navarasa-GGUF

GGUF
gemma
llama.cpp
indic
Inference Endpoints
Model card Files Community
Indic-gemma-2b-finetuned-sft-Navarasa-GGUF / README.md
iAkashPaul's picture
iAkashPaul
Update README.md
04cab8b verified
preview code
|
raw
history blame
1.22 kB
metadata
license: mit
tags:
  - gemma

GGUF for Indic-gemma-2b-finetuned-sft-Navarasa

This model from Telugu-LLM-Labs is based on google/gemma-2b and has been LoRA finetuned on 9 Indian languages and English instruction datasets

git clone https://huggingface.co/iAkashPaul/Indic-gemma-2b-finetuned-sft-Navarasa-GGUF # & cd into it, update paths accordingly
 
./main --file prompt.md --lora ./models/ggml-adapter-model.bin --lora-base ./models/indic-llm_Q8.gguf

./main --file prompt.md -m ./models/merged_indic_llm_Q8.gguf -ngl 99

Prompt template for Instruction adherence-

Save this to a file(ex. prompt.md) & load it with the main executable.

### Instruction: Translate following sentence to Kannada.

### Input: This model is developed by Telugu LLM Labs

## Response:

Performance

  • LORA+BASE (not merged)

    • ./server --lora ./models/ggml-adapter-model.bin --lora-base ./models/indic-llm_Q8.gguf -m ./models/indic-llm_Q8.gguf

  • Merged model

    • ./server -ngl 20  -m ./models/merged_indic_llm_Q8.gguf