TinyLlama 1.1B LLM RAG Research Chatbot llamaindex Colab Demo Small LLM Amazing performance
ฝัง
- เผยแพร่เมื่อ 8 ก.ย. 2024
- If you like to support me financially, It is totally optional and voluntary. Buy me a coffee here: www.buymeacoff...
“The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. I try out TinyLlama 1.1B LLM as part of a RAG based research chatbot created using llamaindex. We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.”
I try out the model as part of a RAG based research chatbot
Colab notebook: colab.research...
huggingface.co...
github.com/jzh...
If you like such content please subscribe to the channel here:
www.youtube.co...
Thank you for the tutorial, is normal that the VectorStoreIndex take so long for finish before start the gradio interface?
Depends on the document size
Hi sir u r videos are so useful in my day today tasks is it possible to create an interactive chat bot for csv data set with all open source
Thank You. It should be possible
ModuleNotFoundError: No module named 'llama_index.prompts'
I tried !pip install llama_index, it doesn't work..
try pip install llama_index==0.9.24