Instructions to use bartowski/granite-34b-code-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/granite-34b-code-instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/granite-34b-code-instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/granite-34b-code-instruct-GGUF", dtype="auto")

llama-cpp-python

How to use bartowski/granite-34b-code-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/granite-34b-code-instruct-GGUF",
	filename="granite-34b-code-instruct-IQ1_M.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 bartowski/granite-34b-code-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 bartowski/granite-34b-code-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/granite-34b-code-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 bartowski/granite-34b-code-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/granite-34b-code-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 bartowski/granite-34b-code-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/granite-34b-code-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 bartowski/granite-34b-code-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/granite-34b-code-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/granite-34b-code-instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/granite-34b-code-instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/granite-34b-code-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": "bartowski/granite-34b-code-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/granite-34b-code-instruct-GGUF:Q4_K_M

SGLang

How to use bartowski/granite-34b-code-instruct-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 "bartowski/granite-34b-code-instruct-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": "bartowski/granite-34b-code-instruct-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 "bartowski/granite-34b-code-instruct-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": "bartowski/granite-34b-code-instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bartowski/granite-34b-code-instruct-GGUF with Ollama:
```
ollama run hf.co/bartowski/granite-34b-code-instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use bartowski/granite-34b-code-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 bartowski/granite-34b-code-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 bartowski/granite-34b-code-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 bartowski/granite-34b-code-instruct-GGUF to start chatting

Docker Model Runner
How to use bartowski/granite-34b-code-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/granite-34b-code-instruct-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/granite-34b-code-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/granite-34b-code-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-34b-code-instruct-GGUF-Q4_K_M

List all available models

lemonade list

Chat template - use with Ollama?

by smcleod - opened May 21, 2024

Discussion

smcleod

May 21, 2024

This model seems pretty strong for coding and it's quite quick for it's size.

One thing I struggled with was it's weird chat template (thanks IBM 🙄), after messing around quite a bit with the Ollama TEMPLATE and PARAMETER stop settings I've found this to be the most effective, although I'm certain it could be further improved if anyone has any ideas?

SYSTEM "You are an AI assistant and expert coder, carefully consider the users question and complete their request making sure you meet all requirements. Output your responses with markdown formatting unless requested otherwise."

PARAMETER temperature 0.7
PARAMETER num_keep -1

TEMPLATE """{{ if .System }}System: {{ .System }}{{ end }}

<|start_header_id|>Question: <|end_header_id|>
{{ .Prompt }}<|eot_id|>

<|start_header_id|>Answer: <|end_header_id|>
{{ .Response }}<|endoftext|>"""

PARAMETER stop "<|endoftext|>"
PARAMETER stop "<|eot_id|>"
PARAMETER stop "<end of code>"

As always - thanks for the great GGUFs!

bartowski

Owner May 21, 2024

Interesting, you find that it needs the start and end header_id? Their given prompt doesn't use it so that surprises me. I'll have to give it a bit of testing on my own to see, but thanks for the heads up for others!

smcleod

May 21, 2024

Good catch! I actually thought it did but you're quite right it doesn't mention it in the docs, not sure what I was thinking when I added that.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment