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

Libraries

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

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kuramot6f/classical-smollm2-sft"
# 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-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

classical-smollm2-sft: chatting with a model that has only read pre-1868 texts

A dialogue fine-tune of classical-smollm2-trunk, a 125M-parameter model trained from scratch only on texts written before 1868. It was fine-tuned on real conversations from classical and Edo-period texts, so it answers in premodern Japanese with replies such as 「いとかしこし」 or 「おかへりなされませ」.

This is an early research checkpoint. It has learned the turn-taking format and to stop after a short reply, but its replies are formulaic and often don't really answer the question.

Usage

The model was trained with this plain-text format; BOS is added by the tokenizer:

<s>user:
{your message}assistant:
{model reply}</s>

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

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

prompt = "user:\nいづこへ行く" + "assistant:\n"
inputs = tok(prompt, return_tensors="pt")          # prepends <s>
out = model.generate(**inputs, max_new_tokens=96, do_sample=True, temperature=0.8, top_p=0.95,
                     eos_token_id=tok.eos_token_id, pad_token_id=tok.pad_token_id)
print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

For multi-turn chat, append assistant:\n{reply}</s> after each reply, then user:\n{next message}assistant:\n. The separators are listed in chat_format.json.

Training

Base: classical-smollm2-trunk at update 27,500, from the learning-rate decay phase. This is slightly earlier than the final trunk checkpoint published in that repo.
Data: the high-quality subset of classical-ja-sft-dialogue: two-speaker scenes with extraction_confidence >= 2 and context_dependence <= 1. That gives 1,426 training scenes from 234 works and 56 validation scenes. The first speaker in a scene becomes user and the other becomes assistant; consecutive turns by the same speaker are merged.
Loss on assistant tokens and EOS only. Full fine-tuning, learning rate 1e-5, batch ≤16, 3 epochs (270 updates).
This checkpoint is update 90 (1 epoch), the one with the lowest validation loss:

update	validation NLL (assistant tokens)
0 (base)	4.570
45	4.322
90 (this model)	4.302
180	4.334
270	4.351

Limitations

Replies are short and generic, and long prompts can cause repetition.
The validation set is small and mostly from Wikisource. No test-set evaluation and no benchmark has been run, and whether fine-tuning made the model forget some of its pretraining has not been checked.
Like the base model, it reflects pre-1868 views and must not be used as a source of facts.
SUMMARY.md has the full training report (in Japanese).

License

Weights and code: Apache-2.0. The fine-tuning data is CC BY-SA 4.0. The base model's training data also includes public-domain and CC BY-NC-SA 3.0 TW (CBETA) texts; see classical-smollm2-trunk.

Downloads last month: 17

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for kuramot6f/classical-smollm2-sft

Base model

kuramot6f/classical-smollm2-trunk

Finetuned

(1)

this model

kuramot6f
/

classical-smollm2-sft