Instructions to use LiquidAI/LFM3-1.7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM3-1.7B-Base with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM3-1.7B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM3-1.7B-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM3-1.7B-Base", trust_remote_code=True, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LiquidAI/LFM3-1.7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM3-1.7B-Base"
# 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/LFM3-1.7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM3-1.7B-Base

SGLang

How to use LiquidAI/LFM3-1.7B-Base 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/LFM3-1.7B-Base" \
    --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/LFM3-1.7B-Base",
		"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/LFM3-1.7B-Base" \
        --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/LFM3-1.7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM3-1.7B-Base with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM3-1.7B-Base
```

Single-file CMF build for local inference (Rust; Vulkan, Metal, CPU)

by infosave - opened 12 days ago

Discussion

infosave

12 days ago

We packaged LFM3-1.7B-Base as single CMF files that run with cortiq, a Rust inference engine with no Python, on Vulkan/DX12, Metal or the CPU.

Files: https://huggingface.co/infosave/LFM3-1.7B-Base-cmf — q8_2f (1.76 GB, wikitext-2 ppl 9.556, the same as bf16) and q4tp (0.93 GB, 9.984).

Decoding runs at 166 tok/s (q8_2f) / 228 tok/s (q4tp) on an NVIDIA A40 and 84 tok/s (q4tp) on an Apple M4.

cargo install cortiq-cli
cortiq ppl lfm3-1.7b-base-q8_2f.cmf -f text.txt --tokens 4096
cortiq run lfm3-1.7b-base-q8_2f.cmf --prompt "What is the capital of France?"

(cortiq 0.8.50)

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