Instructions to use s3nh/Novocode7b-v3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use s3nh/Novocode7b-v3-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="s3nh/Novocode7b-v3-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("s3nh/Novocode7b-v3-GGUF", dtype="auto")

llama-cpp-python

How to use s3nh/Novocode7b-v3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="s3nh/Novocode7b-v3-GGUF",
	filename="novocode7b-v3.Q3_K_S.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 s3nh/Novocode7b-v3-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf s3nh/Novocode7b-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf s3nh/Novocode7b-v3-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 s3nh/Novocode7b-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf s3nh/Novocode7b-v3-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 s3nh/Novocode7b-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf s3nh/Novocode7b-v3-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 s3nh/Novocode7b-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf s3nh/Novocode7b-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/s3nh/Novocode7b-v3-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use s3nh/Novocode7b-v3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "s3nh/Novocode7b-v3-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s3nh/Novocode7b-v3-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/s3nh/Novocode7b-v3-GGUF:Q4_K_M

SGLang

How to use s3nh/Novocode7b-v3-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 "s3nh/Novocode7b-v3-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": "s3nh/Novocode7b-v3-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 "s3nh/Novocode7b-v3-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": "s3nh/Novocode7b-v3-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use s3nh/Novocode7b-v3-GGUF with Ollama:
```
ollama run hf.co/s3nh/Novocode7b-v3-GGUF:Q4_K_M
```

Unsloth Studio new

How to use s3nh/Novocode7b-v3-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 s3nh/Novocode7b-v3-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 s3nh/Novocode7b-v3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for s3nh/Novocode7b-v3-GGUF to start chatting

Docker Model Runner
How to use s3nh/Novocode7b-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/s3nh/Novocode7b-v3-GGUF:Q4_K_M
```

Lemonade

How to use s3nh/Novocode7b-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull s3nh/Novocode7b-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Novocode7b-v3-GGUF-Q4_K_M

List all available models

lemonade list

Original model card

Buy me a coffee if you like this project ;)

Description

GGUF Format model files for This project.

GGUF Specs

GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:

Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information. Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models. mmap compatibility: models can be loaded using mmap for fast loading and saving. Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used. Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user. The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for inference or for identifying the model.

inference

User: Tell me story about what is an quantization and what do we need to build. User 0: Sure, I'd be happy to help!

So, in the context of deep learning, quantization refers to the process of representing the weights and activations of a neural network using lower-precision data types, such as 8-bit or 16-bit integers, instead of the traditional 32- or 64-bit floating-point numbers. This can significantly reduce the size of the model and make it more efficient to train and deploy on resource-constrained devices.

To build a quantized neural network, you'll need to

Original model card

Downloads last month: 1

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit