Models Converted to fp16
- LLama2-chat-hf-fp16
- LLama3-7b-Instruct Model with fp16
- LLama3-70B-Instruct Model with fp16
Quantized models:
https://fossies.org/linux/llama.cpp/examples/imatrix/README.md
https://www.databricks.com/sites/default/files/2024-04/Databricks-Big-Book-Of-GenAI-FINAL.pdf
Vectordb
https://medium.com/@zilliz_learn/how-to-evaluate-a-vector-database-86dfdcc67d9b
Chunk Visualization
https://chunkviz.up.railway.app/
Prompting
https://www.promptingguide.ai/ https://learnprompting.org/docs/intro
##MLOPs https://www.databricks.com/sites/default/files/2024-06/2023-10-EB-Big-Book-of-MLOps-2nd-Edition.pdf