Jacob Portes
@jacobianneuro.bsky.social
📤 189
📥 381
📝 0
Research Scientist @MosaicMLxDatabricks. I like it when neuroscience inspires AI 🧠+🖥️
reposted by
Jacob Portes
Andrew Drozdov
8 months ago
We're probably a little too obsessed with zero-shot retrieval. If you have documents (you do), then you can generate synthetic data, and finetune your embedding. Blog post lead by
@jacobianneuro.bsky.social
shows how well this works in practice.
www.databricks.com/blog/improvi...
loading . . .
Improving Retrieval and RAG with Embedding Model Finetuning
Fine-tune embedding models on Databricks to enhance retrieval and RAG accuracy with synthetic data—no manual labeling required.
https://www.databricks.com/blog/improving-retrieval-and-rag-embedding-model-finetuning
1
8
5
reposted by
Jacob Portes
Brett Larsen
11 months ago
What’s the most effective way to add new domain knowledge into an open LLM? A new blog post from my team covers experiments we did at the beginning of the year to start answering this question. It starts, unsurprisingly, with sweeping your learning rate…
www.databricks.com/blog/charact...
loading . . .
Characterizing Datasets and Building Better Models with Continued Pre-Training
https://www.databricks.com/blog/characterizing-datasets-and-building-better-models-continued-pre-training
0
22
9
you reached the end!!
feeds!
log in