Instructions to use LiquidAI/LFM2.5-1.2B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2.5-1.2B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2.5-1.2B-Instruct")
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/LFM2.5-1.2B-Instruct")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-1.2B-Instruct", 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/LFM2.5-1.2B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2.5-1.2B-Instruct"
# 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/LFM2.5-1.2B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct

SGLang

How to use LiquidAI/LFM2.5-1.2B-Instruct 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/LFM2.5-1.2B-Instruct" \
    --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/LFM2.5-1.2B-Instruct",
		"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/LFM2.5-1.2B-Instruct" \
        --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/LFM2.5-1.2B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2.5-1.2B-Instruct with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2.5-1.2B-Instruct
```

LFM2.5-1.2B-Instruct

Commit History

Nov 3 Yesterday

12:36
Add IFBench evaluation result⁠

SaylorTwift HF Staff

Verified signature
ed64424
06:57
Update README.md

mlabonne

Verified signature
51d0915

Aug 24

21:06
Add DSpark

mlabonne

Verified signature
0f604ad

Aug 5

17:01
Fix chat template: render assistant tool_calls (#20)⁠

mlabonne +1: nathanrchn

df58c17

Aug 3

01:26
Update README.md

jimmysmith1919

Verified signature
3d2b14b

Jun 16

09:16
Update LICENSE

mlabonne

Verified signature
868df74

Mar 30

12:48
Fix Try LFM link to use playground.liquid.ai homepage

Paulescu

6314d2b
12:21
Add Discord community link to README

Paulescu

97fd4c6

Mar 28

00:29
Update README.md

mlabonne

Verified signature
e7114d1

Feb 24

13:12
Update README.md

mlabonne

Verified signature
e129ea4

Feb 2

16:24
add GRPO TRL fine-tuning notebook

mlabonne

Verified signature
719098d

Jan 27

16:21
Add GPQA evaluation result (#9)⁠

mlabonne +1: burtenshaw

Verified signature
8c1348a

Jan 26

11:28
Update README.md

mlabonne

Verified signature
8dc4e68

Jan 22

16:45
Update README.md

mlabonne

Verified signature
47c527b

Jan 20

16:35
Update README.md

mlabonne

Verified signature
c20ca41

Jan 19

14:36
Update README.md

mlabonne

Verified signature
43f1e80

Jan 9

05:56
Update README.md

ykhrustalev

Verified signature
286966c
05:55
Upload README.md with huggingface_hub

ykhrustalev

Verified signature
4393ab8

Jan 7

13:41
Update README.md

mlabonne

Verified signature
a4ba0a6

Jan 6

00:29
Add files using upload-large-folder tool

mlabonne

Verified signature
205939a
00:28
initial commit

mlabonne

Verified signature
f3a7622

Commit History

Nov 3 Yesterday

Add IFBench evaluation result⁠

Update README.md

Aug 24

Add DSpark

Aug 5

Fix chat template: render assistant tool_calls (#20)⁠

Aug 3

Update README.md

Jun 16

Update LICENSE

Mar 30

Fix Try LFM link to use playground.liquid.ai homepage

Add Discord community link to README

Mar 28

Update README.md

Feb 24

Update README.md

Feb 2

add GRPO TRL fine-tuning notebook

Jan 27

Add GPQA evaluation result (#9)⁠

Jan 26

Update README.md

Jan 22

Update README.md

Jan 20

Update README.md

Jan 19

Update README.md

Jan 9

Update README.md

Upload README.md with huggingface_hub

Jan 7

Update README.md

Jan 6

Add files using upload-large-folder tool

initial commit