What's Changed (this repo branch)
Sync to Ollama main v0.6.6-rc2
What's Changed (from Ollama)
New models
- IBM Granite 3.3: 2B and 8B models with 128K context length that have been fine-tuned for improved reasoning and instruction-following capabilities.
- DeepCoder: a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
What's Changed
- New, faster model downloading: OLLAMA_EXPERIMENT=client2 ollama serve to try running Ollama with this new downloader with improved performance and reliability when running ollama pull. Please share feedback!
- Fixed memory leak issues when running Gemma 3, Mistral Small 3.1 and other models on Ollama
- Improved performance of ollama create when importing models from Safetensors
- Ollama will now allow tool function parameters with either a single type or an array of types by @rozgo
- Fixed certain out of memory issues from not reserving enough memory at startup
- Fix nondeterministic model unload order by @IreGaddr
- Include the items and $defs fields to properly handle array types in the API by @sheffler
- OpenAI-Beta headers are now included in the CORS safelist by @drifkin
- Fixed issue where model tensor data would be corrupted when importing models from Safetensors
New Contributors
- @drifkin made their first contribution in ollama#10169
- @rozgo made their first contribution in ollama#9434
- @qwerty108109 made their first contribution in ollama#10168
- @IreGaddr made their first contribution in ollama#10185
- @sheffler made their first contribution in ollama#10091
Full Changelog: v0.6.5...v0.6.6-rc2