Instructions to use GhostScientist/semanticwiki-coder-7b-v2-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use GhostScientist/semanticwiki-coder-7b-v2-gguf 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 GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GhostScientist/semanticwiki-coder-7b-v2-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 GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GhostScientist/semanticwiki-coder-7b-v2-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 GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Use Docker

docker model run hf.co/GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GhostScientist/semanticwiki-coder-7b-v2-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": "GhostScientist/semanticwiki-coder-7b-v2-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Ollama
How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with Ollama:
```
ollama run hf.co/GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M
```
Unsloth Desktop

How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with Docker Model Runner:
```
docker model run hf.co/GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M
```

Lemonade

How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Run and chat with the model

lemonade run user.semanticwiki-coder-7b-v2-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GhostScientist/semanticwiki-coder-7b-v2-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 GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GhostScientist/semanticwiki-coder-7b-v2-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "GhostScientist/semanticwiki-coder-7b-v2-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

SemanticWiki Coder 7B v2 — GGUF Q4_K_M

What?

This is the GGUF Q4_K_M quantization of GhostScientist/semanticwiki-coder-7b-v2-merged. It is intended for llama.cpp-compatible tools, including local desktop applications and browser-based interfaces backed by a local llama.cpp server.

The quantized file is approximately 4.46 GB. The original merged F16 GGUF is approximately 15.2 GB and was used as the quantization input.

Why?

GGUF is a convenient distribution format for local inference because it keeps model tensors and runtime metadata together and is supported by llama.cpp. Q4_K_M is a practical quality/size compromise for consumer hardware.

GGUF is a model format, not automatically an in-browser runtime. The most reliable browser workflow is to run llama-server locally and open its WebUI. Direct WebGPU/WebAssembly browser loading is a separate compatibility path and depends on the browser, device memory, and runtime build.

Quick start with llama.cpp

hf download GhostScientist/semanticwiki-coder-7b-v2-gguf \
  --include '*.gguf' \
  --local-dir ./semanticwiki-coder-7b-v2-gguf

llama-server \
  -m ./semanticwiki-coder-7b-v2-gguf/semanticwiki-coder-7b-v2-q4_k_m.gguf \
  -c 8192

Open the local URL printed by llama-server.

For a command-line smoke test:

llama-cli \
  -m ./semanticwiki-coder-7b-v2-gguf/semanticwiki-coder-7b-v2-q4_k_m.gguf \
  -p '<START_OF_CONTEXT>\nclass Greeter:\n    def hello(self):\n        return "hello"\n<END_OF_CONTEXT>\n\n<query>\nExplain this code.\n</query>' \
  -n 256

Provenance

Base model: Qwen/Qwen2.5-Coder-7B-Instruct
Merged source: GhostScientist/semanticwiki-coder-7b-v2-merged
Original adapter: GhostScientist/semanticwiki-coder-7b-v2
Conversion: official llama.cpp convert_hf_to_gguf.py
Quantization: llama.cpp llama-quantize, Q4_K_M
GGUF file type: mixed K-quant, approximately 4.91 bits/weight
Context metadata: 32,768 tokens; start browser testing at 8,192

Limitations

Generated documentation can be incorrect, incomplete, or poorly cited.
Review generated source references against the repository being documented.
This model is not a security auditor.
Do not place secrets or private source code into an untrusted application.
Browser support depends on the runtime and available device memory.

License

The base model is distributed under Apache-2.0. Review the upstream model card and applicable terms before redistribution or commercial use.

Downloads last month: 90

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for GhostScientist/semanticwiki-coder-7b-v2-gguf

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

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

Finetuned

GhostScientist/semanticwiki-coder-7b-v2-merged

Quantized

(2)

this model

GhostScientist
/

semanticwiki-coder-7b-v2-gguf

SemanticWiki Coder 7B v2 — GGUF Q4_K_M

What?

Why?

Quick start with llama.cpp

Provenance

Limitations

License

Model tree for GhostScientist/semanticwiki-coder-7b-v2-gguf

Space using GhostScientist/semanticwiki-coder-7b-v2-gguf 1