Instructions to use Aliguinga01/rule_violation2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Aliguinga01/rule_violation2 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 Aliguinga01/rule_violation2:F16
# Run inference directly in the terminal:
llama cli -hf Aliguinga01/rule_violation2:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Aliguinga01/rule_violation2:F16
# Run inference directly in the terminal:
llama cli -hf Aliguinga01/rule_violation2:F16

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 Aliguinga01/rule_violation2:F16
# Run inference directly in the terminal:
./llama-cli -hf Aliguinga01/rule_violation2:F16

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 Aliguinga01/rule_violation2:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Aliguinga01/rule_violation2:F16

Use Docker

docker model run hf.co/Aliguinga01/rule_violation2:F16

LM Studio
Jan
Ollama
How to use Aliguinga01/rule_violation2 with Ollama:
```
ollama run hf.co/Aliguinga01/rule_violation2:F16
```

Unsloth Studio

How to use Aliguinga01/rule_violation2 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 Aliguinga01/rule_violation2 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 Aliguinga01/rule_violation2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Aliguinga01/rule_violation2 to start chatting

Atomic Chat new
Docker Model Runner
How to use Aliguinga01/rule_violation2 with Docker Model Runner:
```
docker model run hf.co/Aliguinga01/rule_violation2:F16
```

Lemonade

How to use Aliguinga01/rule_violation2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Aliguinga01/rule_violation2:F16

Run and chat with the model

lemonade run user.rule_violation2-F16

List all available models

lemonade list

rule_violation2 / llama.cpp /tools /server /tests /unit /test_basic.py

Aliguinga01

Upload folder using huggingface_hub

4d35814 verified 10 months ago

Raw

History Blame Contribute Delete

2.88 kB

	import pytest
	import requests
	from utils import *

	server = ServerPreset.tinyllama2()


	@pytest.fixture(scope="session", autouse=True)
	def do_something():
	# this will be run once per test session, before any tests
	ServerPreset.load_all()


	@pytest.fixture(autouse=True)
	def create_server():
	global server
	server = ServerPreset.tinyllama2()


	def test_server_start_simple():
	global server
	server.start()
	res = server.make_request("GET", "/health")
	assert res.status_code == 200


	def test_server_props():
	global server
	server.start()
	res = server.make_request("GET", "/props")
	assert res.status_code == 200
	assert ".gguf" in res.body["model_path"]
	assert res.body["total_slots"] == server.n_slots
	default_val = res.body["default_generation_settings"]
	assert server.n_ctx is not None and server.n_slots is not None
	assert default_val["n_ctx"] == server.n_ctx / server.n_slots
	assert default_val["params"]["seed"] == server.seed


	def test_server_models():
	global server
	server.start()
	res = server.make_request("GET", "/models")
	assert res.status_code == 200
	assert len(res.body["data"]) == 1
	assert res.body["data"][0]["id"] == server.model_alias


	def test_server_slots():
	global server

	# without slots endpoint enabled, this should return error
	server.server_slots = False
	server.start()
	res = server.make_request("GET", "/slots")
	assert res.status_code == 501 # ERROR_TYPE_NOT_SUPPORTED
	assert "error" in res.body
	server.stop()

	# with slots endpoint enabled, this should return slots info
	server.server_slots = True
	server.n_slots = 2
	server.start()
	res = server.make_request("GET", "/slots")
	assert res.status_code == 200
	assert len(res.body) == server.n_slots
	assert server.n_ctx is not None and server.n_slots is not None
	assert res.body[0]["n_ctx"] == server.n_ctx / server.n_slots
	assert "params" not in res.body[0]


	def test_load_split_model():
	global server
	server.model_hf_repo = "ggml-org/models"
	server.model_hf_file = "tinyllamas/split/stories15M-q8_0-00001-of-00003.gguf"
	server.model_alias = "tinyllama-split"
	server.start()
	res = server.make_request("POST", "/completion", data={
	"n_predict": 16,
	"prompt": "Hello",
	"temperature": 0.0,
	})
	assert res.status_code == 200
	assert match_regex("(little\|girl)+", res.body["content"])


	def test_no_webui():
	global server
	# default: webui enabled
	server.start()
	url = f"http://{server.server_host}:{server.server_port}"
	res = requests.get(url)
	assert res.status_code == 200
	assert "<!doctype html>" in res.text
	server.stop()

	# with --no-webui
	server.no_webui = True
	server.start()
	res = requests.get(url)
	assert res.status_code == 404