Instructions to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF",
	filename="Qwen2.5-14B-Instruct-F16.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 ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF: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 ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF: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 ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Ollama
How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with Ollama:
```
ollama run hf.co/ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF 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 ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF 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 ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF to start chatting

How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF: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": "ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF: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 ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ThomasBaruzier/Qwen2.5-14B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen2.5-14B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

ThomasBaruzier commited on Sep 19, 2024

Commit

4891dca

verified ·

1 Parent(s): ff1aa1b

Update README.md

Browse files

Files changed (1) hide show

README.md +31 -0

README.md CHANGED Viewed

@@ -25,6 +25,37 @@ All quants were made using the imatrix option and Bartowski's [calibration file]
 # Perplexity table (the lower the better)
 <hr>
 # Qwen2.5-14B-Instruct

 # Perplexity table (the lower the better)
+| Quant   | Size (MB) | PPL     | Size (%) | Accuracy (%) | PPL error rate |
+| ------- | --------- | ------- | -------- | ------------ | -------------- |
+| IQ1_S   | 3441      | 22.0082 | 12.21    | 27.14        | 0.16818        |
+| IQ1_M   | 3693      | 15.079  | 13.11    | 39.62        | 0.1106         |
+| IQ2_XXS | 4114      | 9.6047  | 14.6     | 62.2         | 0.06625        |
+| IQ2_XS  | 4487      | 8.3649  | 15.92    | 71.41        | 0.05574        |
+| IQ2_S   | 4772      | 8.1942  | 16.93    | 72.9         | 0.0548         |
+| IQ2_M   | 5109      | 7.7261  | 18.13    | 77.32        | 0.05177        |
+| Q2_K_S  | 5148      | 8.0641  | 18.27    | 74.08        | 0.0549         |
+| Q2_K    | 5504      | 7.6005  | 19.53    | 78.6         | 0.05146        |
+| IQ3_XXS | 5672      | 6.9285  | 20.13    | 86.22        | 0.04547        |
+| IQ3_XS  | 6088      | 6.721   | 21.6     | 88.88        | 0.04329        |
+| Q3_K_S  | 6352      | 6.8697  | 22.54    | 86.96        | 0.04576        |
+| IQ3_S   | 6383      | 6.6246  | 22.65    | 90.17        | 0.04285        |
+| IQ3_M   | 6597      | 6.6359  | 23.41    | 90.02        | 0.04256        |
+| Q3_K_M  | 7000      | 6.5281  | 24.84    | 91.51        | 0.043          |
+| Q3_K_L  | 7558      | 6.4323  | 26.82    | 92.87        | 0.04211        |
+| IQ4_XS  | 7744      | 6.2005  | 27.48    | 96.34        | 0.04022        |
+| Q4_0    | 8149      | 6.2928  | 28.92    | 94.93        | 0.04095        |
+| IQ4_NL  | 8154      | 6.208   | 28.94    | 96.23        | 0.04032        |
+| Q4_K_S  | 8177      | 6.163   | 29.02    | 96.93        | 0.03976        |
+| Q4_K_M  | 8572      | 6.1311  | 30.42    | 97.43        | 0.03957        |
+| Q4_1    | 8958      | 6.1674  | 31.79    | 96.86        | 0.03981        |
+| Q5_K_S  | 9791      | 6.0411  | 34.75    | 98.88        | 0.03886        |
+| Q5_0    | 9817      | 6.0504  | 34.84    | 98.73        | 0.03895        |
+| Q5_K_M  | 10023     | 6.0389  | 35.57    | 98.92        | 0.03888        |
+| Q5_1    | 10625     | 6.0366  | 37.71    | 98.96        | 0.03885        |
+| Q6_K    | 11564     | 6.0004  | 41.04    | 99.56        | 0.0386         |
+| Q8_0    | 14975     | 5.9821  | 53.14    | 99.86        | 0.03842        |
+| F16     | 28179     | 5.9737  | 100      | 100          | 0.03835        |
 <hr>
 # Qwen2.5-14B-Instruct