ollama Profile picture
https://t.co/1JpLwJ9Bdv
Nov 6, 2024 5 tweets 2 min read
Ollama 0.4 is released with support for Meta's Llama 3.2 Vision (11B and 90B) models. @AIatMeta

See what it can do: 👇👇👇
ollama.com/blog/llama3.2-…Ollama 0.4 is here! Examples of running Llama 3.2 vision:

Reading handwritingImage
Feb 15, 2024 5 tweets 2 min read
Ollama windows preview is here!



Here is how to get started:
- Download + double click to install
- Open your favorite terminal and type ollama run llama2

🧵ollama.com/download/windo…Ollama waving with its head outside a window. We're super excited for the release of Ollama windows preview!! Please have an awesome day! We hope you'll enjoy giving Ollama a try. Thank you. Automatic hardware acceleration!

NVIDIA GPUs or modern CPU instructions like AVX or AVX2 if available.

No virtualization required.
Feb 2, 2024 7 tweets 4 min read
Ollama vision is here.

Welcome to the era of open-source multimodal models. Image In this new Ollama release (v0.1.23), we’ve made improvements to how Ollama handles multimodal models. We hope you’ll like it as much as we do!

It works across the CLI, and Python & JavaScript libraries.

In the CLI? Prompt + Drag and drop your image in.Image
Image
Image
Image
Jan 27, 2024 6 tweets 3 min read
Friday fun with models!

ollama run stablelm2

Stable LM 2 from @StabilityAI, a 1.6 billion parameter small language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.

Thanks @EMostaque and team for the model! It now runs on Ollama.

ollama.ai/library/stable…Image .@motherduck's duckdb-nsql model

ollama run duckdb-nsql

DuckDB-NSQL is a 7 billion parameter text-to-SQL model designed specifically for SQL generation tasks.

ollama.ai/library/duckdb…
Image