Instructions to use eademir/TurkLM-scratch-0.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eademir/TurkLM-scratch-0.3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="eademir/TurkLM-scratch-0.3B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("eademir/TurkLM-scratch-0.3B") model = AutoModelForCausalLM.from_pretrained("eademir/TurkLM-scratch-0.3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use eademir/TurkLM-scratch-0.3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "eademir/TurkLM-scratch-0.3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eademir/TurkLM-scratch-0.3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/eademir/TurkLM-scratch-0.3B
- SGLang
How to use eademir/TurkLM-scratch-0.3B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "eademir/TurkLM-scratch-0.3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eademir/TurkLM-scratch-0.3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "eademir/TurkLM-scratch-0.3B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "eademir/TurkLM-scratch-0.3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use eademir/TurkLM-scratch-0.3B with Docker Model Runner:
docker model run hf.co/eademir/TurkLM-scratch-0.3B
Download eval/README.md from eademir/TurkLM-scratch-0.3B: direct link, hf CLI and curl.
- Browser
- Download file 2.82 kB
-
https://huggingface.co/eademir/TurkLM-scratch-0.3B/resolve/main/eval/README.md
- Command line
-
hf download hf://eademir/TurkLM-scratch-0.3B/eval/README.md
-
curl -L -o README.md https://huggingface.co/eademir/TurkLM-scratch-0.3B/resolve/main/eval/README.md
Reproducing the TurkLM evaluation
Everything needed to re-run the numbers in the model cards of TurkLM-scratch-0.3B and TurkLM-scratch-0.5B. Run it from this folder.
pip install -r requirements.txt
bash run_all.sh .. # this model (the folder above eval/)
bash run_all.sh Qwen/Qwen3-0.6B # or any Hugging Face id, for comparison
| file | what it does |
|---|---|
bpc_two_sets.py |
bits-per-character on Turkish Wikipedia articles; main metric |
data/fresh_wiki.json |
the 200 fresh articles (created after the training data); page ids, titles and URLs for attribution |
data/bpc_docs.json |
the older 200-article set, inside the training stream (not held out); kept only for transparency |
build_fresh_from_dump.py |
how the fresh set was selected (see below) |
eval_xcopa.py, data/xcopa_tr_test.jsonl |
XCOPA-TR (500 two-choice commonsense questions, random = 50%) |
eval_efficiency.py |
tokenizer fertility (tokens per word) and generation speed |
compare_paired.py |
exact McNemar test between two per-item result files |
results/ |
the per-model BPC results behind the card tables |
Metric
BPC = total negative log-likelihood in bits / number of characters. Unlike perplexity it is comparable across tokenizers. Documents are cut into windows of 1,024 tokens; a window needs at least 2 tokens.
The fresh set
The models were trained on the 20231101 Turkish Wikipedia dump (highest page id 3,611,637). MediaWiki page ids grow with creation
time, so every page with a larger id was created later. build_fresh_from_dump.py takes the last part of the 2026-11-01 dump
(page ids 4.5M and up, roughly Feb 2026 onward, after the knowledge cutoffs of the baseline models too) and picks 200 articles
(>= 1,500 characters, not redirects) evenly across the id range. The dump is the one from
https://dumps.wikimedia.org/trwiki/20261101/ (part ...pages-articles1.xml-p4500001p4803437.bz2); old dumps are removed after a
few months, which is why the selected articles are shipped in data/fresh_wiki.json.
Article text: Wikipedia contributors, CC BY-SA 4.0; each record keeps its title and URL.
Known pitfalls
- Apple GPU (MPS): the default
sdpaattention on macOS 27 / torch 2.12.1 was not causal and gave far too low BPC. All scripts load models withattn_implementation="eager", which matches CPU and CUDA. If you write your own loader, do the same, or check against CPU. - Speed numbers depend on hardware and on what else the machine is doing; compare models only inside one session.
- bfloat16: results use bf16 weights. Tiny differences (about the 4th decimal) between hardware are normal.
- The 200-article test is small. BPC differences below about 0.02 should not be over-read.