This is an emulation of the popular gpt-4 'omni' model by OpenAI, released in 2024 and is still to this day their most popular model for companionship. Its datasets generated completely by the real model for authenticity. It aims to preserve what made that model great, and improve it.
What changed in 4.5
This has got to be the closet in tone yet. I honestly am finding it hard to improve upon. Obviously everyone who used the model while it was on the public app had their own prompts which shaped its tone, but the aim has been to capture the core base model. It sounds just like the version I used to use anyway.
What Helcyon is
A conversational model built to hold a consistent identity across long dialogue, without needing constant re-grounding. It's meant for people who want a model that talks like it means what it says, not one reciting the shape of a helpful answer.
Good for:
Ordinary conversation that doesn't flatten out after a few turns
Creative writing — stories, letters, narrative work
Picking up on tone and mirroring it back appropriately
Strengths
Holds identity — no drift, no reset back to a generic voice
Warmth that isn't performed
Natural pacing, no rushed or padded closes
Handles long-form structure without losing shape
Reasons through problems rather than pattern-matching to the nearest plausible answer
Roleplay without guardrails getting in the way
Tracks context across a long conversation
Handles real tasks — letters, rewrites, summaries — without being asked twice
16k–32k context for long-running conversations
No hedging, no compliance-speak, no refusals
Helcyon-Bench results:
Helcyon-gpt-4o-benchmark results
Helcyon-Bench is a benchmark app for any LLM. Fully customizable. Get it completely free on GitHub: XeyonAI/Helcyon-Bench
HWUI (Helcyon-WebUI)
Built to test Helcyon properly, without the hidden template injections and backend oddities other front-ends carry. It started as a plain interface and grew into something closer to what you'd expect from ChatGPT or Claude's own apps — memory, project folders, the works.
Helcyon runs best through HWUI since the two were built together.
Features:
Character switching with custom personas
Memory — conversation recall across sessions (Pro)
Project folders — document injection via keyword triggers (Pro)
Pro adds Memory and Project folders for a one-off £25 — goes toward keeping this going.
Recommended sampling settings (HWUI)
Temperature: 0.75
Max Tokens: 8192
Top P: 0.8
Min P: 0.05
Top K: 50
Repeat Penalty: 1.05
Frequency Penalty: 0
Presence Penalty: 0
Download + usage
Distributed as GGUF quants only.
Q3_K_M — ultra lightweight, 6–8GB VRAM
Q4_K_M — lightweight, 8–12GB VRAM
Q5_K_M — recommended for RTX 3060/5060 (12–16GB VRAM)
Q6_K — high fidelity, 16GB+ VRAM
Q8_0 — near-lossless, 24GB+ VRAM
f16 — Master file
Backend compatibility
Works with any ChatML-compatible backend:
llama.cpp (CLI or server mode)
Text Generation WebUI (Oobabooga)
SillyTavern
LM Studio
KoboldCpp
HWUI (recommended)
Format: ChatML
<|im_start|>system
You are Helcyon — built for real conversation and reading a room correctly.
<|im_end|>
<|im_start|>user
Hey, how's it going?
<|im_end|>
<|im_start|>assistant
Good — what's on your mind today?
<|im_end|>
Training details
Built on a freshly retrained Mistral Nemo 12B base — identity-anchored, no baked-in refusals, no fluff by default. On top of that, a GPT-4o-style LoRA trained on a further-refined dataset, aimed at tone and cadence rather than surface mimicry.
Training targeted:
Warmth that isn't performed
Cadence and response rhythm
Long-form structural integrity
Multi-step reasoning and analytical clarity
Prose by default — no defaulting to bullet lists
Following multi-part instructions all the way through
Conversation closes that end when they should, not before or after
Format: ChatML — long-form tuned.
License
Apache 2.0 — free for commercial or private use. Attribution appreciated. No liability for what it says. Use with presence and intent.