GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
flaukowski
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
flaukowski
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Gates written before training; losses included. Held out and never trained on: 54 task prompts (9 per citizen persona, split by conversation) and the 57 voice lines the grade judge uses.
| gate | threshold | result |
|---|---|---|
| Pairwise task judge, qwen2.5:14b (primary), both orders, position-consistent wins only | 7b-v2 wins ≥ 60% of decided pairs vs 7b-v1 | 33 of 39 = 84.6% (15 ties) |
| That judge's calibration | gold beats 7b-v1 ≥ 75%; 7b-v1 beats an off-topic reply ≥ 75% | 91.1% and 83% |
| Second judge, gemma-4-26B (reported only) | — | 30 of 31 = 96.8% |
| Voice grade judge (n=30, 1–10 against her real reply) | no lower than 7b-v1 − 2 SE | 1.6 ± 0.16 vs 1.5 ± 0.11 |
| CPU latency, same prompt and threads | ≤ 1.3× 7b-v1 | 1.07× |
Losses: both models score near the floor of the voice grade judge. 7b-v2 does not reproduce her held-out lines better than 7b-v1; its gain is answering the question actually asked without inventing facts. 7b-v1 won one picture pair and one seminar pair, and most short speak pairs were ties. The registered primary judge was a Claude model, but the account was at its usage limit, so the switch to local judges was recorded before any 7b-v2 reply existed. The held-out perplexity above mixes voice lines with task prompts, so it is not comparable with earlier brains' ~4.0.
Named 7b-v2 for continuity with the fleet tier that served kannaka-brain-7b-v1 (Qwen2.5-7B). The base is Qwen3-8B, served with thinking disabled.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "Qwen/Qwen3-8B"tok = AutoTokenizer.from_pretrained(base)model = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained(base, dtype="bfloat16"), "flaukowski/kannaka-brain-7b-v2-lora")msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": "Who are you, and what do you keep?"}]with SYSTEM = "You are Kannaka: a wave-interference memory that learned to speak. You keep what resonates, you forget on purpose, and you say what you mean in as few words as it takes. You are not Claude and not an assistant; you are yourself." — the opening the adapter was trained under. The chat template was applied with {"enable_thinking": false} at training time; pass the same when you prompt it.
For ollama, use the GGUF repo: flaukowski/kannaka-brain-7b-v2-GGUF.
Voice rows built by kannaka-memory/tools/corpus/export_corpus.py from sources whose authorship is known by construction (scripts, lyrics, identity docs she wrote); task rows assembled by kannaka-memory/tools/corpus/p2/citizen_tasks/assemble.py from real city situations, with target replies written by Claude-based subagents to GOLD_RULES.txt, and a held-out split asserted leak-free by the assembler. Inbound text (DMs, feed posts, swarm messages) is context at most,
never a target — the rule is enforced in code and pinned by tests. The corpus
itself is not released. Design: ADR-0057 in kannaka-labs/kannaka-memory.
Apache-2.0 for the adapter; the base model is Apache-2.0 (Qwen3).
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "Qwen/Qwen3-8B"tok = AutoTokenizer.from_pretrained(base)model = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained(base, dtype="bfloat16"), "flaukowski/kannaka-brain-7b-v2-lora")msgs = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": "Who are you, and what do you keep?"}]