Instructions to use TheBloke/CodeLlama-34B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeLlama-34B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeLlama-34B-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/CodeLlama-34B-GGUF", dtype="auto")

llama-cpp-python

How to use TheBloke/CodeLlama-34B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/CodeLlama-34B-GGUF",
	filename="codellama-34b.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheBloke/CodeLlama-34B-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 TheBloke/CodeLlama-34B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/CodeLlama-34B-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 TheBloke/CodeLlama-34B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheBloke/CodeLlama-34B-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 TheBloke/CodeLlama-34B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/CodeLlama-34B-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 TheBloke/CodeLlama-34B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/CodeLlama-34B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/CodeLlama-34B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TheBloke/CodeLlama-34B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/CodeLlama-34B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/CodeLlama-34B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/CodeLlama-34B-GGUF:Q4_K_M

SGLang

How to use TheBloke/CodeLlama-34B-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 "TheBloke/CodeLlama-34B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/CodeLlama-34B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TheBloke/CodeLlama-34B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/CodeLlama-34B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use TheBloke/CodeLlama-34B-GGUF with Ollama:
```
ollama run hf.co/TheBloke/CodeLlama-34B-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheBloke/CodeLlama-34B-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 TheBloke/CodeLlama-34B-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 TheBloke/CodeLlama-34B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheBloke/CodeLlama-34B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TheBloke/CodeLlama-34B-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeLlama-34B-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/CodeLlama-34B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/CodeLlama-34B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CodeLlama-34B-GGUF-Q4_K_M

List all available models

lemonade list

GGUF quantize

by YanaS - opened Sep 13, 2023

Discussion

YanaS

Sep 13, 2023

Hi, I am trying to quantize a model, and I see you have achieved it. So, could you share the process? I downloaded the model and llama.cpp.
Then I move the model to the model's folder of llama.cpp and run convert.py file. So I get the gguf file. But then I run
!python /llama.cpp/examples/quantize models/[model-folder]/[model]-f32.gguf /models/llama2-bg/[model]-q4_0.bin q4_0

and I get error: /usr/bin/python3: can't find 'main' module in '/content/llama.cpp/examples/quantize'

I would highly appreciate it if you could help me with this.

abrahamn

Sep 14, 2023

You might have better luck by downloading the llamacpp package from github releases, extract the one that matches your arch then run the quantize from there. What I usually do once I have the built package is $ ./quantize "path/to/model.gguf" "path/to/new_model.gguf" q4_0

YanaS

Sep 14, 2023

I do this in Google Colab:
!git clone https://github.com/ggerganov/llama.cpp
!cd llama.cpp && git pull && make clean && LLAMA_CUBLAS=1 make
!pip install -r llama.cpp/requirements.txt
Is it possible I have to explicitly update llama.cpp after cloning? Or, maybe in Colab there is some other issue I don't notice?

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