✷ The archive · 11 labs · 58 dispatches

The labs

No more opening a dozen official blogs every morning. First-hand releases from OpenAI, Anthropic, DeepMind and the rest, each with its substance pulled out.

51

Ollama LLaVA 1.6 Vision Model Support

Ollama has integrated LLaVA 1.6, enhancing vision capabilities with higher image resolution, improved text recognition, and new model sizes including a 34B parameter version.

52

Ollama Python and JavaScript Libraries Release

Ollama has released official Python and JavaScript libraries to simplify the integration of Ollama's REST API features into applications.

53

Building LLM-Powered Web Apps with Client-Side Technology

Ollama explores the feasibility of building fully local Retrieval-Augmented Generation (RAG) web applications using a combination of browser-based tools and Ollama for local LLM execution.

54

Ollama Official Docker Image Release

Ollama has released an official Docker sponsored open-source image to simplify the deployment of large language models locally.

55

Integrating Local LLMs with Obsidian Notes via Ollama

Ollama demonstrates how to build an Obsidian plugin that uses Llama Index and local LLMs to enable conceptual search and conversational interaction with personal notes.

56

Code Llama Prompting Guide

Ollama provides a technical guide on how to structure prompts for Meta's Code Llama model variations, including Instruct, Code completion, and Python-specific versions.

57

Run Code Llama locally with Ollama

Meta's Code Llama models are now runnable locally via Ollama, offering 7B, 13B, and 34B parameter versions plus code and Python specializations for programming tasks.

58

Running Uncensored Llama 2 Models Locally with Ollama

Ollama enables users to run uncensored versions of Llama 2 and other models locally, removing the alignment constraints that often lead to overly cautious or refusals in standard models.