Instructions to use LiquidAI/LFM2.5-2.6B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2.5-2.6B-Base with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2.5-2.6B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-2.6B-Base")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-2.6B-Base", 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/LFM2.5-2.6B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2.5-2.6B-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/LFM2.5-2.6B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-2.6B-Base

SGLang

How to use LiquidAI/LFM2.5-2.6B-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/LFM2.5-2.6B-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/LFM2.5-2.6B-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/LFM2.5-2.6B-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/LFM2.5-2.6B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2.5-2.6B-Base with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2.5-2.6B-Base
```

Update README.md

by tilgasergey - opened 5 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -69,7 +69,7 @@ LFM2.5-2.6B-Base is the pre-trained text-only checkpoint, used to create all the
 | **[LFM2.5-2.6B](https://huggingface.co/LiquidAI/LFM2.5-2.6B)**          | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers, vLLM, and SGLang.                           |
 | **[LFM2.5-2.6B-GGUF](https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF)** | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage.             |
 | **[LFM2.5-2.6B-ONNX](https://huggingface.co/LiquidAI/LFM2.5-2.6B-ONNX)** | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). |
-| **[LFM2.5-2.6B-MLX](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX)** | MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework.                                           |
 This pre-trained checkpoint is only recommended for tasks that require heavy fine-tuning, like language-specific (e.g., Japanese) or domain-specific (e.g., medical) assistants, training on proprietary data, or experimenting with novel post-training approaches.
@@ -93,7 +93,7 @@ Quick start with Transformers (compatible with `transformers>=5.0.0`):
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
-model_id = "LiquidAI/LFM2.5-2.6B-Base"
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",

 | **[LFM2.5-2.6B](https://huggingface.co/LiquidAI/LFM2.5-2.6B)**          | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers, vLLM, and SGLang.                           |
 | **[LFM2.5-2.6B-GGUF](https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF)** | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage.             |
 | **[LFM2.5-2.6B-ONNX](https://huggingface.co/LiquidAI/LFM2.5-2.6B-ONNX)** | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). |
+| **[LFM2.5-2.6B-MLX](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX-8bit)** | MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework.                                           |
 This pre-trained checkpoint is only recommended for tasks that require heavy fine-tuning, like language-specific (e.g., Japanese) or domain-specific (e.g., medical) assistants, training on proprietary data, or experimenting with novel post-training approaches.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+model_id = "lq-preview/LFM2.5-2.6B-Base"
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",