v0.1.7

Full Changelog: v0.1.6...v0.1.7

v0.1.6

Full Changelog: v0.1.5...v0.1.6

v0.1.5

Full Changelog: v0.1.4...v0.1.5

v0.1.4

Full Changelog: v0.1.3...v0.1.4

v0.1.3

What's new

• params subcommand — extract quantization parameters from template GGUFs without running the full pipeline
  • gguf-clone params ./dir (matches all GGUFs)
  • gguf-clone params ./dir "*UD-IQ1_M*.gguf" (glob patterns, same as config)
  • -o params.json to write to file, stdout by default
• Subcommand-based CLI — run and params as proper subcommands with separate help
  • gguf-clone config.yml still works (backward compat)

v0.1.2

• Remove architecture-specific IGNORE list adapted from llama.cpp
• Use (\d+) wildcard for uniform layers, grouped alternation for mixed layers
• Detect and raise on conflicting tensor qtypes across template GGUFs

v0.1.1

Full Changelog: v0.1.0...v0.1.1

v0.1.0

Full Changelog: https://github.com/spicyneuron/gguf-clone/commits/v0.1.0