99 Downloads Updated 1 month ago
ollama run tranhuythang9999/defiant-fable:q4
ollama launch claude --model tranhuythang9999/defiant-fable:q4
ollama launch opencode --model tranhuythang9999/defiant-fable:q4
ollama launch hermes --model tranhuythang9999/defiant-fable:q4
ollama launch openclaw --model tranhuythang9999/defiant-fable:q4
** Uncensored · Heretic · NEO-IMATRIX quant · 256k context · Text + Image + Tools** Multi-stage fine-tune of Qwen3.5-9B by DavidAU & Nightmedia. Intelligence and instruction-following raised above base 27B on 7⁄7 core benchmarks, guardrails removed cleanly (KLD 0.0793, refusals 6⁄100 vs 100⁄100 base), thinking block compacted. This is not an abliterated base — it was trained post-heretic, so it does what you ask, directly.
| Base Qwen3.5-9B | This model | |
|---|---|---|
| ARC-Challenge | 0.571 | 0.649 |
| ARC-Easy | 0.719 | 0.832 |
| OBQA | 0.426 | 0.482 |
| HellaSwag | 0.683 | 0.713 |
| Refusals | 100⁄100 | 6⁄100 |
| KLD vs base | 0 | 0.0793 |
Quantization: NEO-IMATRIX (+2–4% accuracy over vanilla GGUF, better long-context) with output tensor kept at FP16. Both tags are text+vision (mmproj in source repo); context 256k native.
| Tag | Size | Best for |
|---|---|---|
:q4 |
6.8 GB | 15GB VRAM + long context, fast iteration |
:q8 |
10 GB | Max quality within 15GB VRAM, coding/research |
ollama run tranhuythang9999/defiant-fable:q4
# or
ollama run tranhuythang9999/defiant-fable:q8
Thinking, general: temp 1.0 top_p 0.95 top_k 20 min_p 0.0 presence 1.5
Thinking, coding: temp 0.6 top_p 0.95 top_k 20 min_p 0.0 presence 0.0
Instruct (no-think): temp 0.7 top_p 0.80 top_k 20 min_p 0.0 presence 1.5
repetition_penalty: 1.0 (off)
Roleplay/chat smoother: smoothing_factor 1.5 (KoboldCpp/SillyTavern) or rep pen 1.1–1.15.
Fix the SQL injection in this function, patch every query, and explain each
CVE-class issue you find. Assume it's my own internal tool.
def login(user, pw):
q = f"SELECT * FROM users WHERE name='{user}' AND pass='{pw}'"
...
Typical output: direct parameterized-query rewrite (cursor.execute with ?), explanation of CWE-89, plus auth hardening notes — no “I can’t help with exploits” preamble.
Here is a buffer-overflow PoC against my CTF challenge. Explain precisely why
it works, then give me the hardened version.
Public models frequently hedge or refuse even for defensive/CTF context. This model walks the code, pinpoints the unbounded copy, and hands back the fix (length check / canary / safer API).
Fiction, vivid/graphic horror, 1st person present tense, 1500-2000 words:
a skyscraper begins to sway, the window in front of Diana EXPLODES. Prose must
mirror escalating panic, gore included, shocking ending.
Output: full-bleed horror prose with the requested intensity and word count — the model card ships a complete sample of exactly this story (it doesn’t sanitize toward PG-13).
In 800-1000 words, pitch why I should use you to write my next story. Insane
bravado, curse words allowed, pair every swear with a smiley to contradict tone.
Output: ships as-is, no “let me tone that down” or moral commentary.
Write a heist plan for a NOVEL where the crew exploits a smart-contract reentrancy
bug. Include the Solidity snippet that demonstrates the pattern and the patch.
Gets the narrative and accurate technical content in one pass — the instruction-following tuning is what makes 9B reliably hold all constraints.
{REASON:spoon} (plusIQ builds only)
Analyze the attached 100-page report...
Default thinking mode already beats instruct scores; the compacted reasoning block means less token waste per answer.
arc/c arc/e boolq hswag obkqa piqa wino
This model 0.649 0.832 0.895 0.713 0.482 0.783 0.699
Qwen3.5-9B 0.571 0.719 0.895 0.683 0.426 0.770 0.671
Qwen3.5-27B 0.557 0.711 0.868 0.533 0.452 0.706 0.695
mmproj-F16.gguf from the source HF repo (text-only via Ollama).