Sublime

DeepSeek Coder comprises a series of code language models trained from scratch on both 87% code and 13% natural language in English and Chinese, with each model pre-trained on 2T tokens. We provide various sizes of the code model, ranging from 1B to 33B versions. Each model is pre-trained on repo-level code corpus by employing a window size of 16K... See more

We’ve created SEVEN advanced retrieval LlamaPacks as templates to help you build advanced RAG 🔥 It’s never been easier; instead of following a notebook, you can now try each technique in ~1 line of code ⚡️ Here’s the full set of techniques below: ⭐️ Hybrid Fusion (vector +... See more