Instructions to use squ11z1/Gravity-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use squ11z1/Gravity-2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="squ11z1/Gravity-2",
	filename="gravity-2-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use squ11z1/Gravity-2 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 squ11z1/Gravity-2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf squ11z1/Gravity-2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf squ11z1/Gravity-2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf squ11z1/Gravity-2: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 squ11z1/Gravity-2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf squ11z1/Gravity-2: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 squ11z1/Gravity-2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf squ11z1/Gravity-2:Q4_K_M

Use Docker

docker model run hf.co/squ11z1/Gravity-2:Q4_K_M

LM Studio
Jan

vLLM

How to use squ11z1/Gravity-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "squ11z1/Gravity-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "squ11z1/Gravity-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/squ11z1/Gravity-2:Q4_K_M

Ollama
How to use squ11z1/Gravity-2 with Ollama:
```
ollama run hf.co/squ11z1/Gravity-2:Q4_K_M
```

Unsloth Studio

How to use squ11z1/Gravity-2 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 squ11z1/Gravity-2 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 squ11z1/Gravity-2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for squ11z1/Gravity-2 to start chatting

How to use squ11z1/Gravity-2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf squ11z1/Gravity-2: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": "squ11z1/Gravity-2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use squ11z1/Gravity-2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf squ11z1/Gravity-2: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 squ11z1/Gravity-2:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use squ11z1/Gravity-2 with Docker Model Runner:
```
docker model run hf.co/squ11z1/Gravity-2:Q4_K_M
```

Lemonade

How to use squ11z1/Gravity-2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull squ11z1/Gravity-2:Q4_K_M

Run and chat with the model

lemonade run user.Gravity-2-Q4_K_M

List all available models

lemonade list

Gravity-2 / load_gravity2.py

squ11z1

Gravity-2 stage-1: VibeThinker-3B with gravity attention (LoRA merged + trained masses)

d3b580b verified 11 days ago

Raw

History Blame Contribute Delete

1 kB

	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from gravity_attention_qwen import patch_qwen_with_gravity

	REPO = "." # or "squ11z1/Gravity-2"
	tok = AutoTokenizer.from_pretrained(REPO)
	model = AutoModelForCausalLM.from_pretrained(REPO, dtype=torch.bfloat16,
	device_map="cuda", attn_implementation="eager")
	patch_qwen_with_gravity(model) # re-enable gravity attention
	masses = torch.load(f"{REPO}/gravity_mass_log.pt", map_location="cuda")
	for i, layer in enumerate(model.model.layers):
	layer.self_attn.gravity_mass_log.data.copy_(masses[f"model.layers.{i}.self_attn.gravity_mass_log"].cuda())
	model.eval()
	ids = tok.apply_chat_template([{"role":"user","content":"What is 24*17?"}],
	add_generation_prompt=True, return_tensors="pt", return_dict=True)["input_ids"].cuda()
	print(tok.decode(model.generate(ids, max_new_tokens=200)[0, ids.shape[1]:], skip_special_tokens=True))