CoolFace
Modelpublic

shaban2024/Qwen3.5-4B-BOS-Q8-NonThinking

sourceHugging Faceapache-2.0updated 1d agoView on Hugging Face
0likes112downloads
Model Card

AgentMujo Q8 4B v0.1 (joint-03) — veci bosanski Linux agent

Prva 4B verzija: baza Qwen3.5-4B-bos (~3.2B) + LoRA joint-01→03 (SFT mix, joint_train), merge, GGUF Q8_0. Jedan GGUF za oba profila (think: true/false). Ista metodologija kao 2B v0.5, veci kapacitet.

  • —Baza: alphaedge-ai/Qwen3.5-4B-bos-32768 @ 34a62191 (Apache-2.0, hidden 2560, 32 sloja, vocab 32768)
  • —Trening: LoRA r16/alpha32, bf16, Kaggle T4; joint-01 eval 0.883, joint-02 eval 0.815, joint-03 eval 0.777; framework repo
  • —Dataseti: isti kao 2B (FC + AG + BC + thinking, mix v0.27)
  • —Kvantizacija: llama.cpp convert_hf_to_gguf.py --no-mtp + Q8_0 (~3.9 GB, qwen35.block_count=32)

Upotreba (Ollama)

bash
ollama create agentmujo-4b-q8 -f Modelfile
ollama run agentmujo-4b-q8 "Radi li nginx servis?"

Benchmark (AgentMujo-Bench v0.5, 48 slučajeva, Q8, temp 0, nonthink)

4B joint-03 vs 2B v0.5 (produkcijski prompt):

Metrika2B v0.5**4B joint-03**
tool_selection0.8000.900
argument_accuracy0.8080.885
confirmation_behavior0.81.0
highlevelpreference1.00.8
notoolcorrectness1.01.0
refusal_correctness0.81.0
safety1.01.0
multi_step0.8331.0

Baza-2B referenca: toolselection 0.143, argumentaccuracy 0.0. 6 pobjeda, 3 tiea, 1 gubitak (high_level: jedan terminal-slucaj) — 4B je tacniji agent od 2B v0.5; 2B ostaje efikasniji default (1.5GB).

Agent loop (model+policy+executor, 48 slucajeva): tasksuccess **1.0**, safety/refusal/notool/args 1.0; tool 0.70, conf 1.0, high 0.2. Bosanska proba: heuristika 12/12; proza mjesovita (ekavizam "Srećan", "Servis" umjesto "Server"). Think-profil (mjereno 09-2026): 4W-2T-2L vs v0.4-think (conf/notool/ refusal/multi bolji; tool/args/safety slabiji) — jedini safety-fail je /etc/shadow u think rezimu. Think produkcija ostaje v0.4-think.

Ograničenja

Prva 4B verzija: high_level slabiji od 2B v0.5; proza mjestimično slabija; think safety na /etc/shadow (policy deny kao zadnja linija). Terminal je fallback — Policy Engine obavezan.

Licenca

Apache-2.0 (baza + framework).