Instructions to use genshiai-daichi/med-lfm2.5-1.2b-autocomplete with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use genshiai-daichi/med-lfm2.5-1.2b-autocomplete with Transformers:

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

pipe = pipeline("text-generation", model="genshiai-daichi/med-lfm2.5-1.2b-autocomplete")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("genshiai-daichi/med-lfm2.5-1.2b-autocomplete")
model = AutoModelForCausalLM.from_pretrained("genshiai-daichi/med-lfm2.5-1.2b-autocomplete")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use genshiai-daichi/med-lfm2.5-1.2b-autocomplete with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "genshiai-daichi/med-lfm2.5-1.2b-autocomplete"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "genshiai-daichi/med-lfm2.5-1.2b-autocomplete",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/genshiai-daichi/med-lfm2.5-1.2b-autocomplete

SGLang

How to use genshiai-daichi/med-lfm2.5-1.2b-autocomplete 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 "genshiai-daichi/med-lfm2.5-1.2b-autocomplete" \
    --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": "genshiai-daichi/med-lfm2.5-1.2b-autocomplete",
		"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 "genshiai-daichi/med-lfm2.5-1.2b-autocomplete" \
        --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": "genshiai-daichi/med-lfm2.5-1.2b-autocomplete",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use genshiai-daichi/med-lfm2.5-1.2b-autocomplete with Docker Model Runner:
```
docker model run hf.co/genshiai-daichi/med-lfm2.5-1.2b-autocomplete
```

アクセス申請（研究・評価目的）

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

本モデルは日本語の医療テキストで学習した、医療文の補完モデルです。利用は LFM Open License v1.0 に従います（年商1,000万ドルを超える企業の商用利用は Liquid AI との個別契約が必要）。本モデルは下書き支援であり、自律的な診断・処方の判断には使用しないでください（出力は必ず医療者が確認）。以下に同意のうえ申請してください。内容を確認し、手動で承認します。

Gated model

You can list files but not access them

Preview of files found in this repository

アクセス申請（研究・評価目的）

Gated model You can list files but not access them

Gated model

You can list files but not access them