CetinLM-1B-Base

<p align="center"> <img src="https://raw.githubusercontent.com/xertxetin/CetinLM/refs/heads/main/docs/cetinlm-logo-lq.png" alt="CetinLM" width="250"> </p> <h1 align="center">CetinLM Base-v1</h1> <p align="center"> <strong>From-scratch language-model pretraining · public model card · active research</strong> </p> <p align="center"> <img src="https://img.shields.io/badge/parameters-1.18B-111111" alt="1.18B parameters"> <img src="https://img.shields.io/badge/tokenizer-48K_custom-111111" alt="48K custom tokenizer"> <img src="https://img.shields.io/badge/context-2K-111111" alt="2K training context"> <img src="https://img.shields.io/badge/stage-base_pretraining-111111" alt="Base pretraining"> </p> <p align="center"> <a href="https://cetinlm.meforcetechnology.com/research"><strong>→ View the latest CetinLM research & training metrics</strong></a> </p>

---

Model card

CetinLM Base-v1 is a ~1.18B-parameter decoder-only language model trained from scratch with the custom CetinTokenizer-v1 tokenizer.

This page describes the public Base-v1 research lineage. The model is still in the base-pretraining stage; instruction following, assistant behavior and later post-training capabilities are separate stages and should not be inferred from pretraining loss alone.

<table> <tr> <td width="33%" valign="top"><strong>Model</strong><br><br>~1.18B decoder-only parameters.</td> <td width="33%" valign="top"><strong>Tokenizer</strong><br><br>CetinTokenizer-v1 · 48K vocabulary.</td> <td width="33%" valign="top"><strong>Context</strong><br><br>2K active Base-v1 training context.</td> </tr> </table>

The frozen Base-v1 corpus contains approximately 11.39B unique training tokens. Processed-token count measures training exposure and is not the same thing as unique corpus size.

---

Latest metrics live on the Research page

CetinLM is actively training, which means the latest token count, validation loss, perplexity, per-dataset measurements and sampled generation-health results continue to change.

To avoid leaving stale numbers scattered across model cards and repositories, the canonical current metrics are maintained here:

CetinLM Research → cetinlm.meforcetechnology.com/research

Historical measurements below remain intentionally preserved as a public reference snapshot.

---

Archived public snapshot — 5.15B

This is an archived reference point, not the current training state. For the current checkpoint, use the live Research page above.

Reference training trajectory

Across the archived 4.80B → 5.15B window, held-out validation loss moved from 2.513649 → 2.496678.

---

Sampled generation-health reference

At 5.00B, a separate 1,000-generation web-balanced-v1 evaluation recorded:

• loop incidents: 5/1000 (0.500%)
• severe loops: 0/1000 (0.000%)
• repetition burden: 0.020% — 20 / 101,597 generated tokens
• EOS stops: 393/1000
• length limit: 602/1000
• average generated tokens: 101.6

The 25-case RAW GREEDY STRESS PROBE is intentionally harsher and is not presented as a user-facing loop rate.

For newer sampled-behavior runs, see CetinLM Research.

---

Training-stage boundary

Base-v1 is the pretrained foundation, not the finished assistant.

The current model card should therefore be read as evidence about:

• language-model pretraining progress;
• held-out validation behavior;
• dataset-level validation trends;
• EOS boundary health;
• mechanical generation diagnostics.

It should not be read as a final claim about instruction following, reasoning, coding, factuality, safety, tool use or assistant quality. Those belong to later post-training and dedicated evaluations.

---

CetinLM Live

CetinLM Live is a separate interactive runtime layer developed around the model stack. Public work includes realtime speech, synchronized text/audio interaction, interruption handling, local voice processing and persistent interaction research.

Live/runtime development does not alter Base-v1 checkpoint accounting or the frozen training lineage.

Speech-runtime licensing

Optional Live speech uses separately licensed third-party software. Resemble AI Chatterbox Multilingual V3 is used for text-to-speech under its upstream MIT License. CetinLM does not claim ownership of Chatterbox.

Public third-party provenance and license notices are maintained with the CetinLM GitHub public research archive.

---

Research links

• Latest metrics & research telemetry: cetinlm.meforcetechnology.com/research
• Project website: cetinlm.meforcetechnology.com

---

<p align="center"> <strong>CetinLM · build from scratch, measure continuously, keep the evidence public.</strong> </p>