Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text generation

iris-engine

by Emre Vergili emrevrg/iris-engine

iris-engine is an open-weight model for text generation from Emre Vergili, released under Apache License 2.0. Its published files total 19.4 KB.

Herhangi bir HF modelini, bellek bütçesi altında, bit-birebir (kayıpsız) çalıştır. Model bitleri hiç atılmaz; katman katman seçmeli yüklenir, kullanılınca bırakılır. Tepe bellek = tek katman, model boyutu değil.

Parameters—
Context—
Weights19.4 KB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Emre Vergili, published under apache-2.0, revision 2fb8b9a1db23.

Herhangi bir HF modelini, bellek bütçesi altında, bit-birebir (kayıpsız) çalıştır. Model bitleri hiç atılmaz; katman katman seçmeli yüklenir, kullanılınca bırakılır. Tepe bellek = tek katman, model boyutu değil. Çıktı, tam-yükle referansla logit düzeyinde birebir aynı. Bit sıkıştırma değil (yüksek-entropi ağırlıkların kayıpsız sınırı ~1,3×'tir — fizik). Kayıpsız dağıtım/akış: yerleşik ayak-izi = model/N, N sınırsız. Ölçümler bulutta (Kaggle/Colab) gerçek koşudan. iris verify ile kendin doğrula. 1. Böl — model katman/tensör düzeyinde parçalanır. 2. Akıt — her parça gerektiğinde belleğe alınır, kullanılınca bırakılır (disk-offload yok). 3. Birleştir — aynı ağırlık + aynı sıra = tam modelle…

Read Emre Vergili's full model card

IRIS — kayıpsız dağıtık model motoru

Herhangi bir HF modelini, bellek bütçesi altında, bit-birebir (kayıpsız) çalıştır. Model bitleri hiç atılmaz; katman katman seçmeli yüklenir, kullanılınca bırakılır. Tepe bellek = tek katman, model boyutu değil. Çıktı, tam-yükle referansla logit düzeyinde birebir aynı.

Bit sıkıştırma değil (yüksek-entropi ağırlıkların kayıpsız sınırı ~1,3×'tir — fizik). Kayıpsız dağıtım/akış: yerleşik ayak-izi = model/N, N sınırsız.

Kur

pip install iris-engine        # yayınlandığında
# veya kaynaktan:
pip install ./iris

Kullan

# 7B modeli katman-akışıyla çalıştır (tek katman kadar RAM/VRAM)
iris run Qwen/Qwen2.5-7B --prompt "Görelilik nedir?" --max-new 40

# çıktı tam-yükle ile bit-birebir mi? ölç:
iris verify Qwen/Qwen2.5-7B

Koddan:

from iris.engine import IrisModel, verify_bit_exact

m = IrisModel("Qwen/Qwen2.5-7B")          # GPU varsa kullanır
print(m.generate("Merhaba, ", max_new_tokens=40))
print("tepe bellek:", m.peak_gb, "GB")

print(verify_bit_exact("Qwen/Qwen2.5-7B"))
# {'max_logit_abs_diff': 0.0, 'bit_exact_fraction': 1.0, 'next_token_identical': True, ...}

Neden AirLLM/Colibri yerine

AirLLM Colibri IRIS
Kalite kayıplı olabilir kayıplı akış bit-birebir 0.0
Aynı ayak-izinde — 28/48 sapar 48/48 kesin
Disk okuma/token 2,62 GB — 0,66 GB (7,4× az)
Ölçek tek makine tek makine tek + N node dağıtık

Ölçümler bulutta (Kaggle/Colab) gerçek koşudan. iris verify ile kendin doğrula.

Nasıl çalışır

  1. Böl — model katman/tensör düzeyinde parçalanır.
  2. Akıt — her parça gerektiğinde belleğe alınır, kullanılınca bırakılır (disk-offload yok).
  3. Birleştir — aynı ağırlık + aynı sıra = tam modelle bit-birebir çıktı.

Apache-2.0 · Norovox Labs

Identity and Version

Repository
emrevrg/iris-engine
Publisher
Emre Vergili
Task
Text generation
Modality
Text
Library
iris-engine
Parameters
Not stated by the source
Languages
tr, en
Revision
2fb8b9a1db2387e6b5e4ed789e9a80dc338f28f2
First published
2026-09-19
Last updated
2026-09-20

Files and Weights

6 files, 19.4 KB in total.

Configuration3 files · 14.9 KB
Documentation1 file · 2.2 KB
Other1 file · 807 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
__init__.pyConfiguration327 B —
cli.pyConfiguration3.5 KB —
engine.pyConfiguration11.0 KB —
README.mdDocumentation2.2 KB —
pyproject.tomlOther807 B —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download from Emre Vergili

Released by Emre Vergili through its official repository on Hugging Face. Read the license.

Questions About iris-engine

Can I use iris-engine commercially?

Yes. iris-engine is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers