Try LFM • Documentation • LEAP

LFM2.5-1.2B-Base-ONNX

ONNX export of LFM2.5-1.2B-Base for cross-platform inference.

LFM2.5 is a hybrid architecture combining multiplicative gates and short convolutions, optimized for edge deployment with fast inference on CPU, GPU, and NPU hardware. This is the base (pretrained) model for text completion tasks.

Recommended Variants

Precision	Size	Platform	Use Case
Q4	~1.2GB	WebGPU, Server	Recommended for most uses
FP16	~2.4GB	WebGPU, Server	Higher quality
Q8	~1.7GB	Server only	Balance of quality and size

• WebGPU: Use Q4 or FP16 (Q8 not supported)
• Server: All variants supported

Model Files

onnx/
├── model.onnx              # FP32
├── model_fp16.onnx         # FP16
├── model_q4.onnx           # Q4 (recommended)
└── model_q8.onnx           # Q8

Python

Installation

pip install onnxruntime transformers numpy huggingface_hub
# or with GPU support:
pip install onnxruntime-gpu transformers numpy huggingface_hub

Inference

import numpy as np
import onnxruntime as ort
from huggingface_hub import hf_hub_download
from transformers import AutoTokenizer

# Download model (Q4 recommended)
model_id = "LiquidAI/LFM2.5-1.2B-Base-ONNX"
model_path = hf_hub_download(model_id, "onnx/model_q4.onnx")
data_path = hf_hub_download(model_id, "onnx/model_q4.onnx_data")

# Load model and tokenizer
session = ort.InferenceSession(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

# Prepare text completion input
prompt = "The quick brown fox"
input_ids = np.array([tokenizer.encode(prompt, add_special_tokens=True)], dtype=np.int64)

# Initialize KV cache
ONNX_DTYPE = {"tensor(float)": np.float32, "tensor(float16)": np.float16, "tensor(int64)": np.int64}
cache = {}
for inp in session.get_inputs():
    if inp.name in {"input_ids", "attention_mask", "position_ids"}:
        continue
    shape = [d if isinstance(d, int) else 1 for d in inp.shape]
    for i, d in enumerate(inp.shape):
        if isinstance(d, str) and "sequence" in d.lower():
            shape[i] = 0
    cache[inp.name] = np.zeros(shape, dtype=ONNX_DTYPE.get(inp.type, np.float32))

# Check if model uses position_ids
input_names = {inp.name for inp in session.get_inputs()}
use_position_ids = "position_ids" in input_names

# Generate tokens
seq_len = input_ids.shape[1]
generated_tokens = []

for step in range(50):  # max tokens
    if step == 0:
        ids = input_ids
        pos = np.arange(seq_len, dtype=np.int64).reshape(1, -1)
    else:
        ids = np.array([[generated_tokens[-1]]], dtype=np.int64)
        pos = np.array([[seq_len + len(generated_tokens) - 1]], dtype=np.int64)

    attn_mask = np.ones((1, seq_len + len(generated_tokens)), dtype=np.int64)
    feed = {"input_ids": ids, "attention_mask": attn_mask, **cache}
    if use_position_ids:
        feed["position_ids"] = pos

    outputs = session.run(None, feed)
    next_token = int(np.argmax(outputs[0][0, -1]))
    generated_tokens.append(next_token)

    # Update cache
    for i, out in enumerate(session.get_outputs()[1:], 1):
        name = out.name.replace("present_conv", "past_conv").replace("present.", "past_key_values.")
        if name in cache:
            cache[name] = outputs[i]

    if next_token == tokenizer.eos_token_id:
        break

print(prompt + tokenizer.decode(generated_tokens, skip_special_tokens=True))

WebGPU (Browser)

Installation

npm install @huggingface/transformers

Enable WebGPU

WebGPU is required for browser inference. To enable:

1. Chrome/Edge: Navigate to chrome://flags/#enable-unsafe-webgpu, enable, and restart
2. Verify: Check chrome://gpu for "WebGPU" status
3. Test: Run navigator.gpu.requestAdapter() in DevTools console

Inference

import { AutoModelForCausalLM, AutoTokenizer, TextStreamer } from "@huggingface/transformers";

const modelId = "LiquidAI/LFM2.5-1.2B-Base-ONNX";

// Load model and tokenizer
const tokenizer = await AutoTokenizer.from_pretrained(modelId);
const model = await AutoModelForCausalLM.from_pretrained(modelId, {
  device: "webgpu",
  dtype: "q4",  // or "fp16"
});

// Prepare input (text completion)
const prompt = "The quick brown fox";
const inputIds = tokenizer.encode(prompt);

// Generate with streaming
const streamer = new TextStreamer(tokenizer, { skip_prompt: false });
const output = await model.generate({
  input_ids: inputIds,
  max_new_tokens: 50,
  do_sample: false,
  streamer,
});

console.log(tokenizer.decode(output[0], { skip_special_tokens: true }));

WebGPU Notes

• Supported: Q4, FP16 (Q8 not supported on WebGPU)

License

This model is released under the LFM 1.0 License.