Instructions to use Luigi/lfm2.5-350m-cursor-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Luigi/lfm2.5-350m-cursor-en with Transformers:

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

pipe = pipeline("text-generation", model="Luigi/lfm2.5-350m-cursor-en")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Luigi/lfm2.5-350m-cursor-en")
model = AutoModelForCausalLM.from_pretrained("Luigi/lfm2.5-350m-cursor-en", 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

llama.cpp

How to use Luigi/lfm2.5-350m-cursor-en with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Use Docker

docker model run hf.co/Luigi/lfm2.5-350m-cursor-en:Q4_K_M

LM Studio
Jan

vLLM

How to use Luigi/lfm2.5-350m-cursor-en with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Luigi/lfm2.5-350m-cursor-en"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Luigi/lfm2.5-350m-cursor-en",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Luigi/lfm2.5-350m-cursor-en:Q4_K_M

SGLang

How to use Luigi/lfm2.5-350m-cursor-en 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 "Luigi/lfm2.5-350m-cursor-en" \
    --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": "Luigi/lfm2.5-350m-cursor-en",
		"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 "Luigi/lfm2.5-350m-cursor-en" \
        --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": "Luigi/lfm2.5-350m-cursor-en",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Luigi/lfm2.5-350m-cursor-en with Ollama:
```
ollama run hf.co/Luigi/lfm2.5-350m-cursor-en:Q4_K_M
```

Unsloth Studio

How to use Luigi/lfm2.5-350m-cursor-en with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Luigi/lfm2.5-350m-cursor-en to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Luigi/lfm2.5-350m-cursor-en to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Luigi/lfm2.5-350m-cursor-en to start chatting

How to use Luigi/lfm2.5-350m-cursor-en with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Luigi/lfm2.5-350m-cursor-en:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Luigi/lfm2.5-350m-cursor-en with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Luigi/lfm2.5-350m-cursor-en:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Luigi/lfm2.5-350m-cursor-en with Docker Model Runner:
```
docker model run hf.co/Luigi/lfm2.5-350m-cursor-en:Q4_K_M
```

Lemonade

How to use Luigi/lfm2.5-350m-cursor-en with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Run and chat with the model

lemonade run user.lfm2.5-350m-cursor-en-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Luigi/lfm2.5-350m-cursor-en with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Luigi/lfm2.5-350m-cursor-en:Q4_K_M

Run Hermes

hermes

Atomic Chat

LFM2.5-350M CURSOR Agent — English meeting-notes editor

A fine-tuned Liquid LFM2.5-350M (linear-attention, 350M params, ~215 MB at Q4_K_M) that runs an agentic meeting-summarization protocol (CURSOR): it streams a meeting transcript chunk-by-chunk and emits edit operations that curate one evolving set of structured, timestamp-anchored meeting notes — instead of passively summarizing a window.

This is the English model of a per-language pair; the Chinese-Traditional model is at Luigi/lfm2.5-350m-cursor-zh.

The task: CURSOR, not map-reduce

Classic map-reduce summarization (independent per-window digests → merge → shrink) produces locally-correct but globally-disconnected notes: it cannot say how a decision evolved. CURSOR streams the transcript and gives the model exactly one job per step: look at the current notes (STATE) and the next transcript block (CHUNK), and revise:

per step i:
  input:   SYS + STATE (current notes) + CHUNK_i (transcript block)
  output:  edit ops — ADD / UPD / DEL / NOP / TITLE
  harness: validates, applies, caps, advances
end:       optional VERIFY/ANCHOR sweep (judge-backed faithfulness backstop) → render

Because STATE is the only memory (no conversation history crosses steps), temporal integration becomes revising a visible earlier bullet (UPD) — the property that makes the protocol learnable at sub-1B scale. The deterministic harness owns the final word.

Output format (NOTES v2)

TITLE: Office move decision
SUMMARY:
- Move to Building B agreed after discussion [5:10]
DECISIONS:
- Relocate the office to Building B [5:10]
ACTIONS:
- S2: circulate the move checklist (due: Friday) [6:02]
OPEN:
- Parking allocation for Building B [7:40]
TOPICS:
- Office move [0:00]

Every bullet ends with the [m:ss] of the transcript line that supports it.

Training

stage	data	purpose
SFT	teacher traces (Gemma-4-31B replaying the real harness, judge-filtered), screen-structured synthetic meetings (revision chains, deadlines, trap topics), real transcripts (QMSum, MeetingBank) at 2048 and 128-token chunks	learn the protocol: op grammar, state-gated UPD/DEL, anchor copying, content selection
phase-2	real-transcript traces upsampled ×3 (the evaluation distribution), low LR (2e-5), 2 epochs, continuing from the G1-passing checkpoint	fix fabrication on real meetings (the synthetic/real distribution gap)

Full fine-tune, bf16, completion-only loss, 4096 context. The per-language split exists because a 350M model holds one language's full protocol at a time (measured seesaw); the composite (en + zh, ~430 MB total) stays inside the on-device envelope.

Evaluation (T1 tier, n=20, paired vs a 9B map-reduce baseline)

metric	result
G1 capability screen (decision chain, deadlines, anchors, trap)	PASS (valid-op 100%)
FAITH-claim	+1.05 (14/2/2, p=0.004)
INVERT (notes stating the opposite of the transcript)	0 / 20 (baseline: 3)
FAITH-anchor	+0.40
SYNTH (meeting-level insight)	+0.50 (at the +0.5 gate)
prefill vs baseline	0.51x

Judges: local gpt-oss-20b (FAITH/INVERT, 3× majority), qwen3.6-35B (COVER/SYNTH) — judge family ∉ {student, teacher}. The VERIFY/ANCHOR sweep (harness-side, judge-backed) is part of the deployed pipeline and is what turns 12/20 raw inversions into 0/20.

Quick start (with the project harness)

The model is a component of the CURSOR pipeline in agentic-summarizer; it speaks the harness's op grammar. Minimal use:

# via the project's eval/screen.py (text grammar, greedy)
python eval/screen.py --base-url http://127.0.0.1:8080 --lang en

Served via llama.cpp:

llama-server -m lfm2.5-350m-cursor-en.Q4_K_M.gguf \
  --n-gpu-layers 999 --ctx-size 4096 --temp 0 --jinja

The GGUF (Q4_K_M) and the HF safetensors are both in this repo.

Intended use

Meeting/transcript → structured, timestamp-anchored notes (decisions, actions, open questions, topics)
On-device: 350M params, ~215 MB Q4_K_M, 4k context — fits a 785 MB envelope with room for a bigger sweep budget

Limitations

English only (see the zh model for Chinese-Traditional); each language model holds one language's protocol
4k context per step: ~2048-token chunks with a ≤600-token state
Trained with synthesized clocks (150 wpm): anchors are internally consistent but the wall-clock values are not real; FAITH-anchor on real audio is unmeasured
zh training data is synthetic-only (VCSum unobtainable); contested zh is unmeasured
The base model's license is the LFM Open License v1.0 — redistribution requires the license text and attribution (included in this repo)

Model

Base: LiquidAI/LFM2.5-350M
Architecture: LFM2.5 (linear attention), 16 layers, hidden 1024
Parameters: 350M (268M trainable in SFT)
Context: 4096 (trained) / 128k (architecture)
Quantization: Q4_K_M GGUF included (~215 MB)

License

This model is a derivative of LFM2.5-350M under the LFM Open License v1.0 (included in this repo). Training data is synthetic and public-corpus derived (QMSum, MeetingBank); no personal data. Distributed under the same license with attribution to Liquid AI, Inc.

Downloads last month: -

Safetensors

Model size

0.4B params

Tensor type

F32

BF16

Model tree for Luigi/lfm2.5-350m-cursor-en

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Quantized

(55)

this model