Instructions to use weblab-LLM-M/AscleLM-1-10B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use weblab-LLM-M/AscleLM-1-10B with Transformers:

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

pipe = pipeline("text-generation", model="weblab-LLM-M/AscleLM-1-10B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("weblab-LLM-M/AscleLM-1-10B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use weblab-LLM-M/AscleLM-1-10B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "weblab-LLM-M/AscleLM-1-10B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weblab-LLM-M/AscleLM-1-10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/weblab-LLM-M/AscleLM-1-10B

SGLang

How to use weblab-LLM-M/AscleLM-1-10B 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 "weblab-LLM-M/AscleLM-1-10B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weblab-LLM-M/AscleLM-1-10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "weblab-LLM-M/AscleLM-1-10B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weblab-LLM-M/AscleLM-1-10B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use weblab-LLM-M/AscleLM-1-10B with Docker Model Runner:
```
docker model run hf.co/weblab-LLM-M/AscleLM-1-10B
```

AscleLM-1-10B へのアクセス申請 / Request access to AscleLM-1-10B

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

AscleLM-1-10B は、研究目的限定で配布される、日本語医療分野に特化した研究用の大規模言語モデルです。
本モデルの重みは別添の利用規約（LICENSE / Terms of Use。日本語版を正本とします）のもとで提供されます。
アクセスを申請する前に以下の各項目をよくお読みいただき、すべてに同意いただける場合のみ申請してください。

AscleLM-1-10B is a Japanese medical-specialized research LLM distributed under its own Terms of Use
(research-use only; the Japanese text is the authoritative version). Please read all of the items below
carefully and request access only if you agree to all of them.

同意事項 / Terms you must agree to

研究目的限定での利用 / Research-use only
本モデルを研究目的のみで利用し、商用サービスの提供には利用しません。
I will use this model for research purposes only, and will not use it to provide commercial services.
実臨床では使用しない / No direct clinical use
実際の臨床現場における疾患の診断、治療方針の決定、健康への助言など、医療行為に直接利用しません。
利用は医療専門家による適切な判断の補助となる情報提供にとどめます。また、患者等の個人情報や特定個人の
診断対象となりうる情報を入力しません。
I will not use the model directly for medical acts (diagnosis, treatment decisions, health advice) in real
clinical settings, will limit use to assisting medical professionals' judgment, and will not input patients'
personal information or information identifying specific individuals.
安全性・有効性が未検証であることの理解 / Acknowledgment that safety and efficacy are unverified
本モデルは実臨床における安全性・有効性の検証が十分に行われていないことを理解しています。
I understand that the safety and efficacy of this model have not been sufficiently verified in clinical practice.
無保証・免責の了承 / No warranty; limitation of liability
本プログラムは現状有姿（as is）で提供され、開発者が正確性・完全性・最新性・品質等についていかなる保証も
行わず、本モデルの利用または利用不能により生じた一切の損害について責任を負わないことに同意します。
I agree that the Program is provided "as is," the developers provide no warranty, and are not liable for any
damages arising from use or inability to use this model.
薬機法等の遵守 / Compliance with the Pharmaceuticals and Medical Devices Act (PMD Act)
本モデルを用いて医療用途の製品を開発する場合、当該製品が医療機器プログラムとして薬機法の規制対象となりうる
ことを理解し、必要に応じて PMDA に相談します。
If I develop a product for medical use, I understand it may be regulated as medical device software under the PMD Act,
and I will consult the PMDA as needed.
base 段階の制限の理解 / Understanding of base-stage limitations
本モデルが base（事前学習）段階であり、文末（EOD/EOS）トークン出力の不安定さや繰り返し出力等の既知の制限が
あることを理解しています。
I understand this is a base (pre-trained) model with known limitations such as unstable end-of-sequence (EOD/EOS)
token output and repetition.
利用規約・ライセンスと帰属の遵守 / Terms of Use, license and attribution compliance
本モデル（重み）の利用規約（LICENSE / Terms of Use）を遵守します。また、同梱されるトークナイザ（Qwen3 由来）
およびモデルコード（NVIDIA Nemotron-H / Hugging Face Transformers の Mamba-2 実装由来）が Apache License 2.0 で
あることを理解し、再配布・改変時には各由来元（Qwen Team / NVIDIA Corporation / HuggingFace Inc.）の著作権表示・
ライセンス条項・NOTICE を保持します。
I will comply with the Terms of Use for the weights, and will retain the copyright notices, license terms, and
NOTICE of the bundled tokenizer (from Qwen3) and model code (from NVIDIA Nemotron-H / the Hugging Face Transformers
Mamba-2 implementation; Qwen Team / NVIDIA Corporation / HuggingFace Inc.), all under Apache License 2.0, when
redistributing or modifying those components.
再配布の禁止 / No redistribution
本モデルおよびその改変物を再配布せず、本プログラムを用いた商用サービスの提供、再利用モデルの生成、
学習データの再現・復元・推定を行いません。
I will not redistribute the model or its modifications, and will not provide commercial services, generate reuse
models, or attempt to reproduce/restore/infer the training data using it.
正確な情報の提供・法令遵守 / Accurate information and legal compliance
本申請にあたり正確な情報を提供し、適用される法令および研究倫理指針を遵守して利用します。
I will provide accurate information in this request and comply with all applicable laws and research ethics guidelines.

Gated model

You can list files but not access them

Preview of files found in this repository

AscleLM-1-10B へのアクセス申請 / Request access to AscleLM-1-10B

同意事項 / Terms you must agree to

Gated model You can list files but not access them

Gated model

You can list files but not access them