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

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

.gitattributes

View File

				`@@ -0,0 +1 @@`
				`*.gguf filter=lfs diff=lfs merge=lfs -text`