Instructions to use kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned")
model = AutoModelForCausalLM.from_pretrained("kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned")
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

vLLM

How to use kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned

SGLang

How to use kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned 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 "kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned" \
    --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": "kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned",
		"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 "kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned" \
        --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": "kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned with Docker Model Runner:
```
docker model run hf.co/kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned
```

LiquidAI/LFM2-1.2B-Extract finetuned on Japanese content to output JSON with PII. The model should output only single json with four fields:

{
    "full_name": "name of the person",
    "company_name": "name of the company",
    "address": "address of the plance",
    "phone_number": "phone number"
}

Coded during Liquid AI hackathon in Tokyo.

Evaluations

Evaluation on test split of stockmark/ner-wikipedia-dataset:

Test accuracy on raw model using wiki dataset: 0.9100 --> 1.0 after fine-tunning.

That dataset is somehow simple. We generated 64 samples of long contracts containing PII in Japanese. We used it only to evaluate the final perfomrance of the models

Test accuracy on raw model using OUR dataset: 0.5781 --> 0.9688 after fine-tunning.

Evaluation methodology

We use an exact match on generated JSON. The output of SLM must be a valid JSON with exactly four required fields, no less, no more.

Model Details

Developed by: @kainoj, @valeriosalvucci and @gangadhara691
Language(s) (NLP): Japanese
License: lfm1.0
Finetuned from model: LiquidAI/LFM2-1.2B-Extract
Finetued on dataset: stockmark/ner-wikipedia-dataset

Downloads last month: 7

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned

Base model

LiquidAI/LFM2-1.2B

Finetuned

LiquidAI/LFM2-1.2B-Extract

Finetuned

(1)

this model

kainoj
/

LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned

Evaluations

Evaluation methodology

Model Details

Model tree for kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned

Dataset used to train kainoj/LiquidAI-LFM2-1.2B-Extract-ja-pii-finetuned