Instructions to use kuramot6f/classical-smollm2-trunk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kuramot6f/classical-smollm2-trunk with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kuramot6f/classical-smollm2-trunk")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kuramot6f/classical-smollm2-trunk")
model = AutoModelForCausalLM.from_pretrained("kuramot6f/classical-smollm2-trunk", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kuramot6f/classical-smollm2-trunk with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kuramot6f/classical-smollm2-trunk"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuramot6f/classical-smollm2-trunk",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kuramot6f/classical-smollm2-trunk

SGLang

How to use kuramot6f/classical-smollm2-trunk 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 "kuramot6f/classical-smollm2-trunk" \
    --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": "kuramot6f/classical-smollm2-trunk",
		"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 "kuramot6f/classical-smollm2-trunk" \
        --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": "kuramot6f/classical-smollm2-trunk",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kuramot6f/classical-smollm2-trunk with Docker Model Runner:
```
docker model run hf.co/kuramot6f/classical-smollm2-trunk
```

classical-smollm2-trunk: a language model that has only read pre-1868 texts

A 125M-parameter language model trained from scratch on about 1 billion tokens of texts written before 1868: classical Japanese, Edo-period Japanese and Literary Chinese. It has never seen modern Japanese, English or anything from the web.

It is a research artifact for studying what a model learns from premodern text alone: its vocabulary, its "world knowledge" and its style. It also gives a period-faithful baseline for working with historical documents. It is a base model: it continues text and does not follow instructions. For a conversational version, see classical-smollm2-sft.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "kuramot6f/classical-smollm2-trunk"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype=torch.bfloat16).eval()

inputs = tok("春はあけぼの", return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=64, do_sample=True, top_p=0.95, temperature=0.8)
print(tok.decode(out[0], skip_special_tokens=True))

trust_remote_code=True is needed only for the small SentencePiece tokenizer wrapper (classical_tokenizer.py). The model is a standard LlamaForCausalLM.

Model


architecture	Llama (SmolLM2-135M shape): 30 layers, hidden 576, 9 heads / 3 KV heads, MLP 1536
parameters	124.6M (tied input/output embeddings)
context	8,192 positions (trained on 2,048-token sequences)
vocabulary	32,000, classical-ja-tokenizer
training tokens	1.00B: NDL 440M, Kanripo 427M, Wikisource 108M, Minna de Honkoku 25M

Training

Data: classical-ja-pretrain, train split.
30,518 updates, bf16, AdamW (weight decay 0.1), warmup-stable-decay learning-rate schedule. Single GPU, PyTorch + 🤗 Transformers + Accelerate.
Data mixture: most of training sampled about 50% NDL, 48.5% Kanripo, 1.25% Wikisource and 0.25% Minna de Honkoku. During the final learning-rate decay (updates 24,415–30,518), the mixture moved toward the curated literary sources: 65% Wikisource, 15% Minna de Honkoku, 10% NDL, 10% Kanripo.
This repo holds the final checkpoint. training_config.json has the full configuration and metrics.jsonl the per-step loss and learning rate.

Limitations

It is small: generations drift and repeat after a few sentences.
About 44% of the training tokens are uncorrected OCR, so the model sometimes reproduces OCR noise.
It knows only what pre-1868 texts say, and their views, including religious, political and social views that may be offensive today. It must not be used as a source of facts.

License

Weights and code: Apache-2.0.

Training data note: the model was trained on texts under several licenses. These are public domain (NDL OCR); CC BY-SA 4.0 (Kanripo, Wikisource, Minna de Honkoku); and CC BY-NC-SA 3.0 TW for CBETA-derived Buddhist texts, about 13% of the corpus tokens. See the dataset LICENSES. The license on the weights does not change the licenses of the training texts. If the model reproduces a passage from its training data, that passage stays under its original license.

Downloads last month: 18

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for kuramot6f/classical-smollm2-trunk

Finetunes

1 model

kuramot6f
/

classical-smollm2-trunk