In this article, we are adding a custom model to Ollama. We take a fine-tuned Hugging Face model, StarCoder2-3B, convert it to GGUF format, add it to local Ollama, and push the model to Ollama hub. ...

In this article, we fine tune the StarCoder2-3B model on an instruction tuning dataset to create a small, performant, and fast local coding LLM. ...

In this article, we explore the important components of the Starcoder and Starcoder 2 paper including the model architecture, the datasets, and benchmark. ...

In this article, we create a custom RAG pipeline from scratch with Sentence Transformer embeddings and using Phi-3 Mini for LLM calls. ...

In this article, we cover the summary of the Phi-3 technical report including the architecture, the dataset curation strategy, benchmarks, and Phi-3 vision capabilities. ...