Instructions to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF", dtype="auto")

llama-cpp-python

How to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF",
	filename="hpc-coder-v2-6.7b-q8_0.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 hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0

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 hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0

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 hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with Ollama:
```
ollama run hf.co/hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-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 hpcgroup/hpc-coder-v2-6.7b-Q8_0-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 hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF to start chatting

Docker Model Runner
How to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0
```

Lemonade

How to use hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.hpc-coder-v2-6.7b-Q8_0-GGUF-Q8_0

List all available models

lemonade list

HPC-Coder-v2-6.7b-Q8_0-GGUF

This is the HPC-Coder-v2-6.7b model with 8 bit quantized weights in the GGUF format that can be used with llama.cpp. Refer to the original model card for more details on the model.

Use with llama.cpp

See the llama.cpp repo for installation instructions. You can then use the model as:

llama-cli --hf-repo hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF --hf-file hpc-coder-v2-6.7b-q8_0.gguf -r "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:" --in-prefix "\n" --in-suffix "\n### Response:\n" -c 8096 -p "your prompt here"

Downloads last month: 10

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF

Base model

hpcgroup/hpc-coder-v2-6.7b

Quantized

(5)

this model

Collection including hpcgroup/hpc-coder-v2-6.7b-Q8_0-GGUF

HPC-Coder-v2 Quantizations

Collection

4 items • Updated Aug 9, 2024