Hugging Face Overview
Telugu-Llama2-7B-v0-Instruct is a 7 billion parameter instruction-tuned model developed by Telugu-LLM-Labs. It is built upon the Telugu-Llama2-7B-v0-Base model and has been fine-tuned using two specific instruction datasets: yahma_alpaca_cleaned_telugu_filtered_and_romanized and teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized. This model is designed to follow instructions and generate responses in Telugu.
Key Capabilities
- Instruction Following: Capable of understanding and executing instructions provided in Telugu.
- Multilingual Support: Processes and generates text in both Romanized Telugu and native Telugu script.
- Contextual Understanding: Demonstrates an ability to summarize and extract information from provided Telugu text, as shown in usage examples.
Usage and Developers
The model expects input in a specific format: ### Instruction: {instruction}\n\n### Input: {input}\n\n## Response: {response}. It is a collaborative effort by Ravi Theja and Ramsri Goutham. Users should note that the model is currently in an experimental phase and is sensitive to parameters and inputs, thus not yet recommended for production environments.