lewisdog/lfm2.5-350m-cogs-ask-GGUF overview
lfm2.5 350m cogs ask A 350M ask student for Cogitarium retrieval QA. Two tasks: decompose : split a question into 1 4 retrieval sub questions → {"subquestions"…
Runs locally from ~218.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | lewisdog/lfm2.5-350m-cogs-ask-GGUF |
|---|---|
| Author | lewisdog |
| Pipeline | text-generation |
| License | other |
| Base model | LiquidAI/LFM2.5-350M |
| Last modified | 2026-07-08T16:44:05.000Z |
Model README
---
license: other
license_name: lfm1.0
license_link: https://huggingface.co/LiquidAI/LFM2.5-350M/blob/main/LICENSE
base_model: LiquidAI/LFM2.5-350M
language:
- en
pipeline_tag: text-generation
tags:
- gguf
- llama.cpp
- cogitarium
---
lfm2.5-350m-cogs-ask
A 350M ask student for Cogitarium retrieval-QA. Two tasks:
- decompose: split a question into 1-4 retrieval sub-questions →
{"subquestions":[...]} - synth: answer strictly from provided wiki notes with inline
[note-id]citations
→ {"answer","citations","abstained"}
Trained on the real cogs serialization — slash note-ids (concepts/planner) and
[[wikilinks]] in note bodies — **plus frontier-teacher-distilled grounded Q&A
generated over the real vault**. Correct on the deployment distribution; needs
no serving hacks.
Serving pins
- temperature 0, repeat_penalty 1.0.
- Emits exact slash note-ids and handles
[[wikilinks]]in bodies natively — you
do NOT need to strip wikilinks or fuzzy-match citations (both were required by the
earlier hyphen-id variant). Feed evidence as `### [note-id] Title
<body>` exactly
as cogs ask builds it.
- Gate abstention upstream. The
abstainedflag is only moderately reliable;
decide "is this answerable?" from retrieval score / the decompose step and don't
depend on the field.
Eval (real vault serialization; grounded citation validity)
Distilled from ~600 frontier-teacher-generated grounded Q&A over the real vault
(plus the re-serialized base set). Grounded-citation validity:
| set | decompose | grounded exact | grounded lenient | abstain |
|-----|:---:|:---:|:---:|:---:|
| deployment vault (aoa, notes seen in training) | 100% | 89% | 89% | 6/11 |
| out-of-domain (unseen clusters) | 100% | 58% | 65% | 3/5 |
Progression as teacher data scaled (out-of-domain grounded strict): vault-aligned
only 38% → +204 teacher 50% → +570 teacher 58%. On the vault it is
actually trained over, grounded citation is ~89%. Data quality/quantity — not
model size — was the binding constraint. Feed evidence as `### [note-id] Title
<body-with-wikilinks>`; citations come back as exact slash-ids, no serving hacks.
Gate abstention upstream (the abstained flag is only moderately reliable). A
strong fast tier; the Qwen3-1.7B student remains the quality tier.
Recommended quant: Q8_0 (379 MB, 509 tok/s on GB10). decompose is flawless at
any quant incl. Q4_K_M (229 MB).
This repo
GGUF quant ladder for llama.cpp (F16 / Q8_0 / Q4_K_M). See the quant table above for the recommended pick and per-quant behavior. Run with --temp 0 and the serving pins noted above.
Base model & license
Fine-tuned from LiquidAI/LFM2.5-350M. Use is governed by the **LFM Open License
v1.0** (lfm1.0) — see the LICENSE in the base repo. This derivative complies with
and inherits those terms; attribution to LiquidAI is retained above.
Provenance
LoRA SFT (TRL) on the Cogitarium distillation datasets, DGX Spark (GB10). Full
methodology, loss curves, eval harnesses and per-quant results: see the project
RESULTS.md. This is the "fast/small tier" of the Cogitarium model picker; the
Qwen3-1.7B students remain the quality tier.
Run lewisdog/lfm2.5-350m-cogs-ask-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models