Instructions to use LiquidAI/LFM2-350M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2-350M with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2-350M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-350M")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-350M")
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 LiquidAI/LFM2-350M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2-350M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LiquidAI/LFM2-350M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2-350M

SGLang

How to use LiquidAI/LFM2-350M 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 "LiquidAI/LFM2-350M" \
    --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": "LiquidAI/LFM2-350M",
		"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 "LiquidAI/LFM2-350M" \
        --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": "LiquidAI/LFM2-350M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2-350M with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-350M
```

transformer not recognizing this model

by joekong0617 - opened Jul 17, 2025

Discussion

joekong0617

Jul 17, 2025

The checkpoint you are trying to load has model type lfm2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

paulpak58

Liquid AI org Jul 17, 2025

bump transformers version

prernaverma

Sep 5, 2025

•

edited Sep 5, 2025

did not work, what should I do

luna-sys

Jan 4

Hi! We just happen to be using the LFM2:0.3B as our model for training, and we noticed this thread, and figured we would share this: https://github.com/luna-system/ada-slm/blob/trunk/train_v9b_pure.py

ada-slm-v9b-pure is a fine-tune of LFM2 that teaches a glyphic language for machine understanding of logic and math! So it's a pretty basic implementation of fine-tuning this particular model!

So the above script is a reference implementation of an LFM2 retrain - complete with ROCm fixes, AND some VERY specific versions of Python and transformers that actually work well for this use case! Open source and public domain! Hope it helps <3

(Thank you LiquidAI team for the architecture! We're using it a LOT in our research!)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment