Eyght v20
Eyght v20 is a fine-tune of Qwen/Qwen2.5-7B-Instruct — the next step in the Eyght
lineage. Packaged as a Q4_K_M GGUF (~4.7 GB) for Ollama.
Built, trained, and owned by Eyght. Free Hugging Face model repository.
Model details
| Base model | Qwen/Qwen2.5-7B-Instruct |
| Architecture | Qwen2ForCausalLM (decoder-only) |
| Parameters | ~7.66 B |
| Format | GGUF (Q4_K_M, ~4.7 GB) |
| Runtime | Ollama / llama.cpp |
| License | Apache-2.0 (fine-tune) |
How to use
ollama run eyght-v20
llama-cli -m eyght-v20.Q4_K_M.gguf -p "Explain async/await in Python." -n 256
Training
LoRA SFT on the Eyght corpus, trained locally by Eyght on a single RTX 4070 Ti (12 GB) with Unsloth (4-bit + LoRA).
Intended use & limitations
- Intended: general assistance, coding, reasoning.
- Not intended: real-time facts, professional advice, very long contexts.
- A 7B fine-tune — verify outputs; it can hallucinate.
License & attribution
- Fine-tune: Apache-2.0. Built, trained, and owned by Eyght.
Citation
@misc{eyght_v20,
title = {Eyght v20: an Eyght fine-tune of Qwen2.5-7B-Instruct},
author = {Eyght},
year = {2026},
howpublished = {Hugging Face, https://huggingface.co/Eyght}
}
Built by Eyght with the local Eyght Veta studio.
🧠 Project Janus — Dual-Loop Cognitive Architecture
This model is designed to operate within Project Janus, a dual-loop cognitive architecture that goes beyond simple prompt-response:
The Core Cognitive Loop
Perceive → Working Memory → Internal Critic → Action → Consolidation
| Phase | Component | Function |
|---|---|---|
| 1. Perceive | Input mapping | Raw data → dense vector space |
| 2. Working Memory | Dynamic scratchpad | Active goal, hypotheses, constraints |
| 3. Internal Critic | Value function | Evaluates outputs before execution (quality + safety) |
| 4. Action | Response delivery | Approved output delivered to the user |
| 5. Consolidation | Durable memory | Successful strategies stored for future retrieval |
Three-Tier Memory
- Episodic Store — append-only memory of past tasks and successes (retrieval-augmented)
- Procedural Skill Library — reusable reasoning patterns compiled into adapters
- Core Value Axioms — frozen safety rules preventing drift as the agent learns
Self-correction + Memory + Safety
The Internal Critic evaluates every draft response against core value axioms before delivery. This enables self-correction, memory-augmented reasoning (RAG), and continuous learning without catastrophic forgetting.
Built by Eyght. Project Janus — a cognitive architecture, not just a model.