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

Libraries

How to use LiquidAI/LFM2-1.2B-RAG with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-1.2B-RAG")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-1.2B-RAG")
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/LFM2-1.2B-RAG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2-1.2B-RAG"
# 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/LFM2-1.2B-RAG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2-1.2B-RAG

SGLang

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

Docker Model Runner
How to use LiquidAI/LFM2-1.2B-RAG with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-1.2B-RAG
```

Which files types can be used?

by Makroshlyta - opened Sep 30, 2025

Discussion

Makroshlyta

Sep 30, 2025

There's no further info in the blog post too.

kalashshah19

Sep 30, 2025

•

edited Sep 30, 2025

I think it's your wish that which file types and how many documents you want to add in the knowledge base of RAG as the embedding and feeding of documents has to be done by you.
The Model is trained for giving answer properly from the provided best matching contextual documents (text content) in the prompt after find the best matched documents while asking the question.

Makroshlyta

Sep 30, 2025

I guess I'm just getting old.
😂

mlabonne

Liquid AI org Sep 30, 2025

Thanks @kalashshah19 !

@Makroshlyta What information is missing for you? I can add it if you have something specific in mind.

kalashshah19

Oct 1, 2025

Thanks @kalashshah19 !

@Makroshlyta What information is missing for you? I can add it if you have something specific in mind.

Welcome !

Makroshlyta

Oct 3, 2025

Well, just basic stuff. TXT? MD? DOC? DOCX? PDF? XLS? XLS? ODT? XML? JSON? RTF?
Back in my day, we just announced this kind of stuff as features. 😆

mlabonne

Liquid AI org Oct 4, 2025

The input provided to the model is always text (like with every LLM). If you want to pass documents, you have to convert them into text beforehand. This is standard practice with RAG systems.

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