GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AhmetcanYvz
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AhmetcanYvz
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Parameters | 1.23B (2048 hidden, 22 layers, 32 heads, 4 KV heads, tied embeddings) |
| Tokeniser | bpe-128k, vocabulary 128,000 |
| Corpus | FineWeb-Edu (English) |
| Tokens | 20B (76,293 steps x 128 sequences x 2048 tokens) |
| Sequence length | 2048 |
| Optimiser | AdamW (0.9, 0.95), weight decay 0.1, grad clip 1.0 |
| LR | 6e-4, 2000 warmup / 2000 decay steps, min ratio 0.01 |
| Precision | bf16 |
| Seed | 42 |
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("AhmetcanYvz/comp-vs-like-1B-bpe-128k")model = AutoModelForCausalLM.from_pretrained("AhmetcanYvz/comp-vs-like-1B-bpe-128k")ids = tok("The capital of France is", return_tensors="pt").input_idsprint(tok.decode(model.generate(ids, max_new_tokens=20)[0]))
The tokeniser is bundled with the model, so no separate download is needed.
This is a research model trained on 20B tokens to study tokenisation. It is not instruction-tuned, not filtered for safety, and not intended for deployment.
https://github.com/Ahmetcanyvz/comp-vs-like
bibtex
@inproceedings{yavuz2026objective,title = {Objective vs. Search: Decomposing What Makes a Good Tokeniser},author = {Yavuz, Ahmetcan and Meister, Clara and Pimentel, Tiago},booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},year = {2026}}