Instructions to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="alesierraalta/codepause-phase7-qwen25-coder-7b-gguf",
	filename="phase7-final-qwen25-coder-7b-f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf: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 alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf: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 alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

Use Docker

docker model run hf.co/alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

LM Studio
Jan

vLLM

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alesierraalta/codepause-phase7-qwen25-coder-7b-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": "alesierraalta/codepause-phase7-qwen25-coder-7b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

Ollama
How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with Ollama:
```
ollama run hf.co/alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16
```

Unsloth Studio new

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-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 alesierraalta/codepause-phase7-qwen25-coder-7b-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 alesierraalta/codepause-phase7-qwen25-coder-7b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alesierraalta/codepause-phase7-qwen25-coder-7b-gguf to start chatting

Pi new

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

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": "alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-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 alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

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 alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

Run Hermes

hermes

Docker Model Runner
How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with Docker Model Runner:
```
docker model run hf.co/alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16
```

Lemonade

How to use alesierraalta/codepause-phase7-qwen25-coder-7b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alesierraalta/codepause-phase7-qwen25-coder-7b-gguf:F16

Run and chat with the model

lemonade run user.codepause-phase7-qwen25-coder-7b-gguf-F16

List all available models

lemonade list

CodePause Phase 7 — Qwen2.5-Coder-7B ThinkAnywhere GGUF

This is a GGUF export of the CodePause Phase 7 model: a Qwen2.5-Coder-7B-Instruct based model fine-tuned with QLoRA for structured code reasoning using <thinkanywhere> blocks.

Intended use

Use in LM Studio or llama.cpp-compatible runtimes for code generation experiments.

Recommended prompt style:

You MUST answer using exactly this format:

<thinkanywhere>
Briefly explain the algorithm, edge cases, and complexity.
</thinkanywhere>

```python
# final code only

Task: Write a Python function longest_unique_substring(s).


## Training summary

- Base model: `Qwen/Qwen2.5-Coder-7B-Instruct`
- Method: QLoRA 4-bit NF4
- Dataset: CodePause Dataset v7
- Dataset size: 150 examples
- Mix: 70% examples with structured reasoning, 30% plain code
- Epochs: 3
- Final artifact: F16 GGUF

## Known limitations

- The model can generate correct code, but `<thinkanywhere>` tag adherence may still require strong prompt formatting.
- This F16 GGUF is large (~15.2GB). Quantized Q4_K_M export is recommended for faster local inference.

## Local loading

Load the `.gguf` file in LM Studio using a Qwen/ChatML-compatible prompt template.

Downloads last month: 80

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

16-bit

Model tree for alesierraalta/codepause-phase7-qwen25-coder-7b-gguf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Quantized

(188)

this model