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", device_map="auto")
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", 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=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
```

paulpak58 commited on Jul 11, 2025

Commit

e9eb554

verified ·

1 Parent(s): cb34594

Bump transformers source v4.54.0.dev0

Browse files

Files changed (3) hide show

README.md +5 -2
config.json +1 -1
generation_config.json +1 -1

README.md CHANGED Viewed

@@ -137,8 +137,11 @@ The candidate with ID 12345 is currently in the "Interview Scheduled" stage for
 ## 🏃 How to run LFM2
-To run LFM2, you need to install Hugging Face [`transformers`](https://github.com/huggingface/transformers) from source (v4.54.0.dev0).
-You can update or install it with the following command: `pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"`.
 Here is an example of how to generate an answer with transformers in Python:

 ## 🏃 How to run LFM2
+> [!WARNING]
+>  ⚠️ Until LFM2 support is merged into the transformers library, it requires setting `trust_remote_code=True` when loading the model.
+To run LFM2, you need Hugging Face [`transformers`](https://github.com/huggingface/transformers) v4.53.0.
+You can update or install it with the following command: `pip install transformers==4.53.0`
 Here is an example of how to generate an answer with transformers in Python:

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "LFM2ForCausalLM"
   ],
   "block_auto_adjust_ff_dim": true,
   "block_dim": 1024,

 {
   "architectures": [
+    "Lfm2ForCausalLM"
   ],
   "block_auto_adjust_ff_dim": true,
   "block_dim": 1024,

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 7,
   "pad_token_id": 0,
-  "transformers_version": "4.53.0.dev0"
 }

   "bos_token_id": 1,
   "eos_token_id": 7,
   "pad_token_id": 0,
+  "transformers_version": "4.54.0.dev0"
 }