Files
homelab/k8s/apps
Story Crater Bot 5470d55b79 reasoning: fix quantization flag mismatch (compressed-tensors, not awq_marlin)
cpatonn's "AWQ-4bit" repo is actually quantized via llm-compressor --
config.json declares compressed-tensors. Passing awq_marlin explicitly
conflicted with the checkpoint's own declared format and 400d at
config-validation time.
2026-08-19 18:23:15 -07:00
..