Instructions to use LiquidAI/LFM2-24B-A2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2-24B-A2B with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2-24B-A2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-24B-A2B")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-24B-A2B", 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/LFM2-24B-A2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2-24B-A2B"
# 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/LFM2-24B-A2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2-24B-A2B

SGLang

How to use LiquidAI/LFM2-24B-A2B 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/LFM2-24B-A2B" \
    --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/LFM2-24B-A2B",
		"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/LFM2-24B-A2B" \
        --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/LFM2-24B-A2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2-24B-A2B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-24B-A2B
```

logan-vegna-shopify commited on Apr 15

Commit

d92fdeb

verified ·

1 Parent(s): 8ef52d1

Extend context to 262144 with YaRN rope scaling

Browse files

Extend max_position_embeddings from 128K to 262144 (256K) using YaRN rope scaling (factor=2.05). This enables vLLM to serve the model with longer context windows.

Files changed (1) hide show

config.json +7 -2

config.json CHANGED Viewed

@@ -52,7 +52,7 @@
     "full_attention",
     "conv"
   ],
-  "max_position_embeddings": 128000,
   "model_type": "lfm2_moe",
   "moe_intermediate_size": 1536,
   "norm_eps": 1e-05,
@@ -72,5 +72,10 @@
   "transformers_version": "5.0.0rc1",
   "use_cache": true,
   "use_expert_bias": true,
-  "vocab_size": 65536
 }

     "full_attention",
     "conv"
   ],
+  "max_position_embeddings": 262144,
   "model_type": "lfm2_moe",
   "moe_intermediate_size": 1536,
   "norm_eps": 1e-05,
   "transformers_version": "5.0.0rc1",
   "use_cache": true,
   "use_expert_bias": true,
+  "vocab_size": 65536,
+  "rope_scaling": {
+    "rope_type": "yarn",
+    "factor": 2.05,
+    "original_max_position_embeddings": 128000
+  }
 }