lukaszraczylo/claude-mnemonic
1
0
Fork 0
mirror of https://github.com/lukaszraczylo/claude-mnemonic.git synced 2026-10-17 05:59:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: replace Git LFS with runtime model download from Hugging Face

Browse Source 
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...
This commit is contained in:
lukaszraczylo
2026-05-26 17:53:30 +01:00
parent c8b462aaec
commit 1a4fea5c17
15 changed files with 431 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/embedding/assets.go
+3 -5
View File
@@ -1,14 +1,12 @@
// Package embedding provides text embedding generation using all-MiniLM-L6-v2.
// Package embedding provides text embedding generation using bge-small-en-v1.5.
package embedding
import (
_ "embed"
)
// Model and tokenizer files - embedded for all platforms
// Tokenizer file - embedded for all platforms (small, not in LFS).
// The ONNX model is downloaded at runtime to ~/.claude-mnemonic/models/.
//
//go:embed assets/model.onnx
var modelData []byte
//go:embed assets/tokenizer.json
var tokenizerData []byte