Instructions to use mishig/xet-gguf-edit-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mishig/xet-gguf-edit-test with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mishig/xet-gguf-edit-test",
	filename="10000mb.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 mishig/xet-gguf-edit-test with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mishig/xet-gguf-edit-test
# Run inference directly in the terminal:
llama-cli -hf mishig/xet-gguf-edit-test

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mishig/xet-gguf-edit-test
# Run inference directly in the terminal:
llama-cli -hf mishig/xet-gguf-edit-test

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 mishig/xet-gguf-edit-test
# Run inference directly in the terminal:
./llama-cli -hf mishig/xet-gguf-edit-test

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 mishig/xet-gguf-edit-test
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mishig/xet-gguf-edit-test

Use Docker

docker model run hf.co/mishig/xet-gguf-edit-test

LM Studio
Jan
Ollama
How to use mishig/xet-gguf-edit-test with Ollama:
```
ollama run hf.co/mishig/xet-gguf-edit-test
```

Unsloth Studio new

How to use mishig/xet-gguf-edit-test 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 mishig/xet-gguf-edit-test 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 mishig/xet-gguf-edit-test to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mishig/xet-gguf-edit-test to start chatting

Pi new

How to use mishig/xet-gguf-edit-test with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mishig/xet-gguf-edit-test

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": "mishig/xet-gguf-edit-test"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mishig/xet-gguf-edit-test with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mishig/xet-gguf-edit-test

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 mishig/xet-gguf-edit-test

Run Hermes

hermes

Docker Model Runner
How to use mishig/xet-gguf-edit-test with Docker Model Runner:
```
docker model run hf.co/mishig/xet-gguf-edit-test
```

Lemonade

How to use mishig/xet-gguf-edit-test with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mishig/xet-gguf-edit-test

Run and chat with the model

lemonade run user.xet-gguf-edit-test-{{QUANT_TAG}}

List all available models

lemonade list

xet-gguf-edit-test / benchmark-results.csv

mishig HF Staff

Upload 8 files

9b9a8b1 verified 8 months ago

raw

history blame contribute delete

503 Bytes

	path,time_seconds,time_minutes
	500mb.gguf,16.84,0.28
	1000mb.gguf,28.11,0.47
	1500mb.gguf,14.51,0.24
	2000mb.gguf,63.58,1.06
	2500mb.gguf,77.68,1.29
	3000mb.gguf,86.01,1.43
	3500mb.gguf,95.35,1.59
	4000mb.gguf,96.84,1.61
	4500mb.gguf,109.46,1.82
	5000mb.gguf,118.75,1.98
	5500mb.gguf,125.96,2.10
	6000mb.gguf,130.67,2.18
	6500mb.gguf,128.47,2.14
	7000mb.gguf,283.87,4.73
	7500mb.gguf,302.53,5.04
	8000mb.gguf,162.38,2.71
	8500mb.gguf,165.12,2.75
	9000mb.gguf,181.57,3.03
	9500mb.gguf,186.59,3.11
	10000mb.gguf,194.16,3.24