Instructions to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Sagicc/granite-8b-code-instruct-Q5_K_M-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 Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_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 Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_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 Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M

Use Docker

docker model run hf.co/Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M

LM Studio
Jan

vLLM

How to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sagicc/granite-8b-code-instruct-Q5_K_M-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": "Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M

SGLang

How to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with Ollama:
```
ollama run hf.co/Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M
```

Unsloth Studio

How to use Sagicc/granite-8b-code-instruct-Q5_K_M-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 Sagicc/granite-8b-code-instruct-Q5_K_M-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 Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M
```

Lemonade

How to use Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF:Q5_K_M

Run and chat with the model

lemonade run user.granite-8b-code-instruct-Q5_K_M-GGUF-Q5_K_M

List all available models

lemonade list

Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF

This model was converted to GGUF format from ibm-granite/granite-8b-code-instruct using llama.cpp after addded support for small Granite Code models in b3026 'llama.cpp release'. Refer to the original model card for more details on the model.

For now only works with llama.cpp

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF --model granite-8b-code-instruct.Q5_K_M.gguf -p "You are an AI assistant"

Server:

llama-server --hf-repo Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF --model granite-8b-code-instruct.Q5_K_M.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m granite-8b-code-instruct.Q5_K_M.gguf -n 128

Downloads last month: 32

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

5-bit

Model tree for Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF

Base model

ibm-granite/granite-8b-code-base-4k

Quantized

(20)

this model

Datasets used to train Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF

Evaluation results

pass@1 on HumanEvalSynthesis(Python)
self-reported

57.900
pass@1 on HumanEvalSynthesis(Python)
self-reported

52.400
pass@1 on HumanEvalSynthesis(Python)
self-reported

58.500
pass@1 on HumanEvalSynthesis(Python)
self-reported

43.300
pass@1 on HumanEvalSynthesis(Python)
self-reported

48.200
pass@1 on HumanEvalSynthesis(Python)
self-reported

37.200
pass@1 on HumanEvalSynthesis(Python)
self-reported

53.000
pass@1 on HumanEvalSynthesis(Python)
self-reported

42.700