No description
Add LoRA field to Linear for transparent adapter injection via model's Forward() path. ApplyLoRA() on Qwen3/Gemma3 wraps target projections. Deterministic param ordering for adapter save/load consistency. MaskedCrossEntropyLoss for training on assistant tokens only. Co-Authored-By: Virgil <virgil@lethean.io> |
||
|---|---|---|
| agentic | ||
| ai | ||
| mcp | ||
| ml | ||
| mlx | ||
| rag | ||
| go.mod | ||
| go.sum | ||
| test-mlx.go | ||
| TEST-RESULTS.md | ||