Harvmaster/autocomplete-model
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Add stage-c and stage-b autocomplete models (Q8_0 GGUF)

Browse Source 
stage-c (default): Qwen2.5-Coder-0.5B fine-tuned for suffix-first FIM with
repo/symbol-context headers. stage-b: same without context headers.
manifest.json lists files, SHA-256s, prompt profiles and the pinned llama.cpp
build for the Local Autocomplete extension's managed mode.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Harvmaster
2026-10-03 15:27:47 +00:00
co-authored by Claude Opus 5.5
commit f8dcf1b7df
7 changed files with 280 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+10
View File
@@ -0,0 +1,10 @@
# Local autocomplete models
Q8_0 GGUF models for the Local Autocomplete VS Code extension (managed mode). The extension reads
`manifest.json`, downloads the selected model, verifies its SHA-256 and runs it locally via llama.cpp.
- **stage-c**: Qwen2.5-Coder-0.5B fine-tuned for suffix-first FIM on TS/Vue + personal code, with symbol-context headers (default). Prompt order spm, context modes: symbols, simple. 531 MB.
- **stage-b**: Previous stage, no context header (plain suffix-first FIM). Prompt order spm, context modes: raw. 531 MB.
Set `localAutocomplete.modelManifestUrl` to the URL of this folder's `manifest.json`.
License: Apache-2.0 (see LICENSE and NOTICE).