LFM2.5-350M-ShellAI-GGUF

ShellAI Bash-command model distilled at the response level from LiquidAI/LFM2.5-2.6B into LiquidAI/LFM2.5-350M.

This repository contains a post-training Q8_0 GGUF. It is not a QAD checkpoint.

The model is trained to emit exactly one command inside:

<shellai-command>command</shellai-command>

General chat anchors, assistant-only loss, LoRA, one training epoch, early stopping, and a pre-publication retention gate are used to reduce catastrophic forgetting. No generated command was executed during dataset construction or evaluation.

Distillation

The two models have different vocabularies (128K teacher versus 65,536 student), so this uses sequence-level response distillation rather than token-logit KL. Teacher candidates that fail the command envelope, primary-utility, or reference- similarity gates fall back to the verified dataset reference.

Evaluation

Held-out repository test split (300 examples, BF16 Transformers):

Model	Exact	Utility match	Token F1	Valid envelope
Base 350M	5.7%	23.0%	0.225	100.0%
Distilled 350M	4.0%	39.7%	0.305	100.0%

Chat retention used 50 non-shell prompts: shell-envelope leakage remained 0.0%; anchor similarity retained 84.9% of baseline.

Q8_0 llama.cpp CPU test (same 50-example subset):

Threads	Token F1	Utility match	Median latency	Decode
1	0.268	36.0%	1278 ms	16.6 tok/s
2	0.268	36.0%	641 ms	32.5 tok/s

License

This is a modified derivative of Liquid AI's LFM2.5 weights and is distributed under the included LFM Open License v1.0. See NOTICE for modification details.