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

Libraries

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

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2-1.2B")
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")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-1.2B")
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 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

davidlms commited on Dec 7, 2025

Commit

d20306b

verified ·

1 Parent(s): c97ace0

Add model-index with benchmark evaluations

Browse files

Added structured evaluation results from README benchmark table:

**Automated Benchmarks:**
- MMLU: 55.23
- GPQA: 31.47
- IFEval (Instruction following): 74.89
- IFBench: 20.7
- GSM8K (Math reasoning): 58.3
- MGSM (Multilingual math): 55.04
- MMMLU (Multilingual MMLU): 46.73

Total: 7 benchmarks across reasoning, instruction-following, and multilingual capabilities.

This enables the model to appear in leaderboards and makes it easier to compare with other models.

Note: PR #6 (Support tool calls) modifies the tokenizer configuration and should not conflict with this metadata addition.

Files changed (1) hide show

README.md +33 -0

README.md CHANGED Viewed

@@ -17,6 +17,39 @@ tags:
 - liquid
 - lfm2
 - edge
 ---
 <center>

 - liquid
 - lfm2
 - edge
+model-index:
+- name: LFM2-1.2B
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Automated Benchmarks
+      type: benchmark
+    metrics:
+    - name: MMLU
+      type: mmlu
+      value: 55.23
+    - name: GPQA
+      type: gpqa
+      value: 31.47
+    - name: IFEval
+      type: ifeval
+      value: 74.89
+    - name: IFBench
+      type: ifbench
+      value: 20.7
+    - name: GSM8K
+      type: gsm8k
+      value: 58.3
+    - name: MGSM
+      type: mgsm
+      value: 55.04
+    - name: MMMLU
+      type: mmmlu
+      value: 46.73
+    source:
+      name: Model README - Automated Benchmarks
+      url: https://huggingface.co/LiquidAI/LFM2-1.2B
 ---
 <center>