Instructions to use finnianx/GPT-5-LFM-2-1.2b-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finnianx/GPT-5-LFM-2-1.2b-Distill with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("finnianx/GPT-5-LFM-2-1.2b-Distill", dtype="auto")

llama-cpp-python

How to use finnianx/GPT-5-LFM-2-1.2b-Distill with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="finnianx/GPT-5-LFM-2-1.2b-Distill",
	filename="GPT5-LFM-2-1.6B-Distill-F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use finnianx/GPT-5-LFM-2-1.2b-Distill with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf finnianx/GPT-5-LFM-2-1.2b-Distill: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 finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf finnianx/GPT-5-LFM-2-1.2b-Distill: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 finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M

Use Docker

docker model run hf.co/finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M

LM Studio
Jan
Ollama
How to use finnianx/GPT-5-LFM-2-1.2b-Distill with Ollama:
```
ollama run hf.co/finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M
```

Unsloth Studio new

How to use finnianx/GPT-5-LFM-2-1.2b-Distill 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 finnianx/GPT-5-LFM-2-1.2b-Distill 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 finnianx/GPT-5-LFM-2-1.2b-Distill to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for finnianx/GPT-5-LFM-2-1.2b-Distill to start chatting

Docker Model Runner
How to use finnianx/GPT-5-LFM-2-1.2b-Distill with Docker Model Runner:
```
docker model run hf.co/finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M
```

Lemonade

How to use finnianx/GPT-5-LFM-2-1.2b-Distill with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull finnianx/GPT-5-LFM-2-1.2b-Distill:Q4_K_M

Run and chat with the model

lemonade run user.GPT-5-LFM-2-1.2b-Distill-Q4_K_M

List all available models

lemonade list

Uploaded model

Developed by: finnianx
License: apache-2.0
Finetuned from model : unsloth/LFM2-1.2B

This lfm2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

A version of LFM 2 1.2b finetuned on the ytz20/LMSYS-Chat-GPT-5-Chat-Response dataset. Mimics the behavior and response style of Chatgpt 5. Trained on responses only to increase accuracy.

Training Parameters

Lora Rank: r = 32
Lora Alpha: lora_alpha = 32
Learning rate: learning_rate = 2e-4
Training epochs: num_train_epochs = 1

Downloads last month: 100

GGUF

Model size

1B params

Architecture

lfm2

Hardware compatibility

1-bit

2-bit

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for finnianx/GPT-5-LFM-2-1.2b-Distill

Base model

LiquidAI/LFM2-1.2B

Finetuned

unsloth/LFM2-1.2B

Quantized

(1)

this model

finnianx
/

GPT-5-LFM-2-1.2b-Distill

Uploaded model

Training Parameters

Model tree for finnianx/GPT-5-LFM-2-1.2b-Distill

Dataset used to train finnianx/GPT-5-LFM-2-1.2b-Distill