Instructions to use TheBloke/CodeLlama-7B-Python-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeLlama-7B-Python-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeLlama-7B-Python-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/CodeLlama-7B-Python-GGUF", dtype="auto")

llama-cpp-python

How to use TheBloke/CodeLlama-7B-Python-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheBloke/CodeLlama-7B-Python-GGUF",
	filename="codellama-7b-python.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TheBloke/CodeLlama-7B-Python-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/CodeLlama-7B-Python-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 TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheBloke/CodeLlama-7B-Python-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-7B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheBloke/CodeLlama-7B-Python-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-7B-Python-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TheBloke/CodeLlama-7B-Python-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/CodeLlama-7B-Python-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-7B-Python-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M

SGLang

How to use TheBloke/CodeLlama-7B-Python-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-7B-Python-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-7B-Python-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-7B-Python-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-7B-Python-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use TheBloke/CodeLlama-7B-Python-GGUF with Ollama:
```
ollama run hf.co/TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheBloke/CodeLlama-7B-Python-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-7B-Python-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-7B-Python-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-7B-Python-GGUF to start chatting

Docker Model Runner
How to use TheBloke/CodeLlama-7B-Python-GGUF with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M
```

Lemonade

How to use TheBloke/CodeLlama-7B-Python-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheBloke/CodeLlama-7B-Python-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CodeLlama-7B-Python-GGUF-Q4_K_M

List all available models

lemonade list

The Q8_0 have mixed tensor types e.g. 'output.norm' is of type Q6_K.

by mukel - opened Aug 25, 2023

Discussion

mukel

Aug 25, 2023

The regular and instruct models are fine, it only happens with this one (the python one).
F32 is fine, but not all consumers of the model support the more esoteric k-quants types.

TheBloke

Owner Aug 25, 2023

OK, If you think that's a bug you'd need to report it to llama.cpp. I just told it to make Q8_0.

However I'm not sure what you mean by 'not all consumers' supporting this? This is GGUF, the new format. Currently most third party libraries do not support GGUF at all. But when they do, they will support everything, the same as llama.cpp. Maybe consumers of GGML don't support mixed tensors in q8_0 (I don't know), but this is not GGML any more.

mukel

Aug 25, 2023

From this PR: https://github.com/ggerganov/llama.cpp/pull/1684
It is stated in the description:
"Not mentioned explicitly above is the fact that with this PR, all quantization variants use 6-bit quantization for the output.weight tensor. This lowers the perplexity of, e.g., Q4_0 by about 0.03 at 7B."
This is a possible explanation why the conversion mix tensor types.

TheBloke

Owner Aug 25, 2023

OK thanks, good to know. I do agree that it's a bit odd that q8_0 would not be 100% q8_0 in all tensors.

I just re-read your first message - are you saying that the Q8_0 models for the 7B and 7B-Instruct models are different? They don't have q6_k in their q8_0? Because they should all be the same, they were all created in exactly the same way.

mukel

Sep 6, 2023

The issue is fixed with the latest update, all tensors are either Q8_0 or F32.

mukel changed discussion status to closed Sep 6, 2023

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