Skip to main content
← Back to Liquid Nanos LFM2-2.6B-Transcript is designed for private, on-device meeting summarization from transcripts. It generates executive summaries, detailed summaries, action items, key decisions, and participant lists.

​
Specifications

PropertyValue
Parameters2.6B
Context Length32K tokens
TaskMeeting Summarization
Recommended Temperature0.3

Executive Summaries

2-3 sentence overviews

Action Items

Extract assigned tasks

Private Processing

On-device summarization

​
Prompting Recipe

Use temperature=0.3 for optimal results. This model requires a specific transcript format.
System Prompt: 
You are an expert meeting analyst. Analyze the transcript carefully
and provide clear, accurate information based on the content.
Input Format: 
<summary_type>

Title: Meeting Title
Date: Date
Time: Time
Duration: Duration
Participants: Names (Roles)

----------

**Speaker 1**: Message
**Speaker 2**: Message
Summary Types:
TypeUser Prompt
Executive summaryProvide a brief executive summary (2-3 sentences) of the key outcomes and decisions.
Detailed summaryProvide a detailed summary covering all major topics, discussions, and outcomes.
Action itemsList the specific action items assigned during this meeting.
Key decisionsList the key decisions that were made during this meeting.
ParticipantsList the participants mentioned in this transcript.
Topics discussedList the main topics and subjects that were discussed.

​
Quick Start

Install:
pip install transformers torch
Run:
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "LiquidAI/LFM2-2.6B-Transcript"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

system_prompt = """You are an expert meeting analyst. Analyze the transcript carefully
and provide clear, accurate information based on the content."""

user_input = """Provide a brief executive summary (2-3 sentences) of the key outcomes and decisions.

Title: Budget Planning Meeting
Date: March 15, 2024
Time: 2:00 PM
Duration: 60 minutes
Participants: Sarah Chen (Finance Director), Mike Johnson (Operations Manager)

----------

**Sarah Chen**: Good afternoon. Let's review our Q1 budget performance.
**Mike Johnson**: Operations came in 5% under budget this quarter.
**Sarah Chen**: For Q2, we need to allocate additional funds for the expansion.
**Mike Johnson**: I'll provide a detailed breakdown by next week."""

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

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.3, do_sample=True)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
See the meeting summarization cookbook example for a complete implementation.