Get up and running with large language models.
External link for Ollama
Palo Alto, California 94301, US
Ollama reposted this
Another year, another leap in LLM app development! 🪄 Our new 2024 LangChain State of AI report uncovers key trends in how developers are building LLM apps. In 2024, we’ve seen a shift from retrieval workflows to multi-step, agentic applications. 🤖 Open-source models are also gaining traction as devs seek more customizable infrastructure. Here's where the AI ecosystem is headed, based on data from LangSmith.👇 Read the full report: https://lnkd.in/g5yd92QW
IBM's latest Granite 3.1 models and their new embedding models are now available via Ollama. Dense models are designed for tool-based use cases. ollama run granite3.1-dense:2b ollama run granite3.1-dense:8b Mixture of expert models are designed for low latency usage. ollama run granite3-moe:1b ollama run granite3-moe:3b Embedding models are smaller in size in comparison to others with similar performance. English only: ollama pull granite-embedding:30m Multilingual: ollama pull granite-embedding:278m Ollama model pages: Dense: https://lnkd.in/g4GkKk9P MoE: https://lnkd.in/gw84-i-e Embedding: https://lnkd.in/gNCvrB-Q
LG AI Research is releasing new models! Exaone 3.5 - English / Korean 7.8B: ollama run exaone3.5 2.4B: ollama run exaone3.5:2.4b 32B: ollama run exaone3.5:32b Model page: https://lnkd.in/gM2DnKCi
Ollama 0.5 is here with structured outputs! This makes it possible to constrain a model’s output to a specific format defined by a JSON schema. Some examples include: - Parsing data from documents - Extracting data from images - Structuring all language model responses - More reliability and consistency than JSON mode Blog post with examples: https://lnkd.in/g5kcQur8 Please update Ollama to 0.5: https://lnkd.in/eXteDfH5 Download the Python or JavaScript libraries: https://lnkd.in/gJf4G4X2 https://lnkd.in/e8Pn9agW
ollama run llama3.3 Meta's Llama 3.3 70B model is available on Ollama, and it has similar performance when compared to Meta's Llama 3.1 405B model. https://lnkd.in/gsqRsxNg
We are so fortunate to have contributors like Sam who worked tirelessly to improve Ollama. Here is his post on how he brought K/V context quantization to Ollama!
[New Blog Post]: Bringing K/V Context Quantisation to Ollama https://lnkd.in/gPxuQvZ4 Shout out to @JMorganCA https://lnkd.in/gbsywHx6 for the reviews and feedback! #AI #LLM #Ollama #Llama #Quantisation
ollama run qwq 💥 an experimental 32B model by the Qwen team that is competitive with o1-mini and o1-preview in some cases. https://lnkd.in/gBbgP2MZ
🎁 Happy 100th Ollama release! In Ollama 0.4.5, we are updating Ollama's Python library! - Python functions can now be provided as tools to models - Strong typing for improved reliability and type safety - New and updated examples for Ollama Learn more about what you can do with Ollama's Python library 0.4: https://lnkd.in/gYF6Uqjy