Skip to content

Nomic v2-moe performs better than embedding gemma and newer#128

Open
scorpion7slayer wants to merge 3 commits intotobi:mainfrom
scorpion7slayer:modelsup
Open

Nomic v2-moe performs better than embedding gemma and newer#128
scorpion7slayer wants to merge 3 commits intotobi:mainfrom
scorpion7slayer:modelsup

Conversation

@scorpion7slayer
Copy link

No description provided.

Nomic v2-moe performs better than embedding gemma and newer

huggingface.co/nomic-ai/nomic-embed-text-v2-moe-GGUF
Copilot AI review requested due to automatic review settings February 6, 2026 23:36
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the default embedding model used by the node-llama-cpp-backed LLM abstraction (src/llm.ts) to point to a different HuggingFace-hosted GGUF model.

Changes:

  • Switch DEFAULT_EMBED_MODEL from embeddinggemma-300M to nomic-embed-text-v2-moe.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant