mirror of
https://github.com/lukaszraczylo/claude-mnemonic.git
synced 2026-06-05 23:03:55 +00:00
lukaszraczylo
1a4fea5c17
Remove ~170MB of model files from the repository (LFS + committed). Models are now downloaded at runtime from Hugging Face on first use and cached to the OS cache directory with progress reporting and retries. - Add internal/models/download.go: runtime downloader with retry, progress bar, checksums - Remove go:embed for ONNX models (keep tokenizers embedded) - Use file-based ONNX session loading instead of byte-slice - Add scripts/download-models.sh for dev/CI model setup - Update Makefile with setup-models target - Update workflow-prepare.sh to download models in CI - Set lfs: false in all CI workflows - SHA256: bge=828e14..., cross-encoder=5d3e70...
13 lines
326 B
Go
13 lines
326 B
Go
// Package embedding provides text embedding generation using bge-small-en-v1.5.
|
|
package embedding
|
|
|
|
import (
|
|
_ "embed"
|
|
)
|
|
|
|
// Tokenizer file - embedded for all platforms (small, not in LFS).
|
|
// The ONNX model is downloaded at runtime to ~/.claude-mnemonic/models/.
|
|
//
|
|
//go:embed assets/tokenizer.json
|
|
var tokenizerData []byte
|