This repository is one member of the Orkhon model family, an auditable from-scratch LLM stack covering tokenizer, pretraining, post-training, evaluation, serving, and Hugging Face export.

Family: Orkhon
Member: istem
Kind: instruct
Interface: chat
Parameters: ~51.4M
Source code: https://github.com/UmutKorkmaz/orkhon
Local model-zoo folder: models/istem-20260620

Family Context

Member	Role	HF repo
`bumin-mini`	4M unified assistant smoke model for EN/TR/Kokturk behavior.	korkmazumut/orkhon-bumin-mini
`tonyuk`	22M unified assistant tuned from the Tonyukuk story base.	korkmazumut/orkhon-tonyuk
`tegin`	22M unified assistant tuned from the former Kultegin instruct model.	korkmazumut/orkhon-tegin
`istem` current	51M unified assistant tuned from the FineWeb-Edu base.	korkmazumut/orkhon-istem
`kashgar`	135M imported assistant slot once local weights are archived.	korkmazumut/orkhon-kashgar
`bunghu`	57M unified EN/TR/Kokturk assistant tuned from the bilingual branch.	korkmazumut/orkhon-bunghu
`tangri`	100M unified EN/TR/Kokturk assistant trained from the mixed Tangri base.	korkmazumut/orkhon-tangri
`qaghan`	Future larger unified assistant slot.	korkmazumut/orkhon-qaghan

Members without archived local weights are skipped by the preparation script.

Intended Use

Inspecting and reproducing the Orkhon training/export path.
Running small local demos on CPU/MPS/CUDA.
Comparing Orkhon family members by training stage and data mix.
Rune-to-Latin Old Turkic transliteration demos.

Not Intended For

Reliable factual QA.
Safety-critical decisions.
Claims of state-of-the-art Turkish or general LLM performance.
Treating Old Turkic transliteration as modern Turkish translation.

Evaluation

Metric	Value
`checkpoint`	runs/istem_unified
`tokenizer`	models/istemi-20260614/tokenizer
`mode`	chat
`tag`	last
`device`	mps
`deterministic_router`	True
`params`	51416960
`step`	2200
`passed`	True
`elapsed_seconds`	3.22

Current benchmark reports in the source repo are smoke baselines unless marked otherwise. Do not treat limit-20 benchmark runs as headline capability claims.

Example Prompt

Bana hangi konularda yardim edebilirsin?

Usage

Install Orkhon from the source repo, then load this exported folder:

pip install git+https://github.com/UmutKorkmaz/orkhon

python

from huggingface_hub import snapshot_download
from orkhon.export.to_hf import load_exported_model
from orkhon.tokenizer import load_tokenizer

path = snapshot_download("korkmazumut/orkhon-istem")
model, cfg = load_exported_model(path, device="cpu")
tok = load_tokenizer(path)

Use orkhon.serve.chat_cli.reply for the unified assistant members.

Files

model.safetensors - exported inference weights
config.json - Orkhon architecture config
tokenizer.json, tokenizer_config.json, special_tokens_map.json
manifest.json - model-zoo metadata from the source repo
samples.txt - saved local samples when available
orkhon_model_card.md - original local model card

Limitations

This is a small research/education model family. The models can repeat, confabulate, and fail outside their narrow data scale. Public demos should keep the claim narrow: Orkhon is an auditable from-scratch stack with a Turkic branch, not a frontier assistant.