LFM2-350M-Extract

350M parameter extraction model (deprecated - use LFM2.5-350M instead)

← Back to Liquid Nanos

This model is deprecated. Use LFM2.5-350M for compact structured extraction with the latest 350M checkpoint.

LFM2-350M-Extract is the fastest extraction model, optimized for edge deployment with strict memory and compute constraints. It delivers structured data extraction with minimal latency.

HFGGUFONNX

Specifications

Property	Value
Parameters	350M
Context Length	32K tokens
Task	Structured Extraction
Output Formats	JSON, XML, YAML

Edge Deployment

Runs on mobile devices

Low Latency

Fastest extraction model

Batch Processing

High-volume extraction

Prompting Recipe

Use temperature=0 (greedy decoding) for best results. This model is intended for single-turn conversations only.

System Prompt Format:

Identify and extract information matching the following schema.
Return data as a JSON object. Missing data should be omitted.

Schema:
- field_name: "Description of what to extract"
- nested_object:
  - nested_field: "Description"

Quick Start

Transformers

Install:

pip install "transformers>=5.2.0" torch accelerate

Run:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "LiquidAI/LFM2-350M-Extract"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

system_prompt = """Identify and extract information matching the following schema.
Return data as a JSON object. Missing data should be omitted.

Schema:
- product: "Product name"
- price: "Price in dollars"
- quantity: "Number of items"
"""

user_input = "Order: 5 units of Widget Pro at $29.99 each"

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": user_input}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0, do_sample=False)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

llama.cpp

Download GGUF:

hf download LiquidAI/LFM2-350M-Extract-GGUF \
  --local-dir ./LFM2-350M-Extract-GGUF

Run:

llama-cli -m ./LFM2-350M-Extract-GGUF/LFM2-350M-Extract-Q4_K_M.gguf \
  -p "Extract product info from: 3 laptops at $999 each" \
  --temp 0