LFM2-1.2B-Extract

1.2B parameter model for structured information extraction from documents

← Back to Liquid Nanos

LFM2-1.2B-Extract is optimized for extracting structured data (JSON, XML, YAML) from unstructured documents. It handles complex nested schemas and multi-field extraction with high accuracy.

HFGGUFONNX

Specifications

Property	Value
Parameters	1.2B
Context Length	32K tokens
Task	Structured Extraction
Output Formats	JSON, XML, YAML

Document Parsing

Extract fields from documents

Data Entry

Automate form filling

Schema Mapping

Complex nested structures

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"

If no system prompt is provided, defaults to JSON. Specify format (JSON, XML, or YAML) and schema for better accuracy.

Quick Start

Transformers

Install:

pip install "transformers>=5.0.0" torch accelerate

Run:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "LiquidAI/LFM2-1.2B-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:
- name: "Person's full name"
- email: "Email address"
- company: "Company name"
"""

user_input = "Contact John Smith at [e-mail]. He works at Acme Corp."

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/LFM2-1.2B-Extract-GGUF \
  --local-dir ./LFM2-1.2B-Extract-GGUF

Run:

llama-cli -m ./LFM2-1.2B-Extract-GGUF/LFM2-1.2B-Extract-Q4_K_M.gguf \
  -p "Extract name and email from: Contact John at [e-mail]" \
  --temp 0