Instructions to use Artefact2/Proctora-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Artefact2/Proctora-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Artefact2/Proctora-GGUF",
	filename="Proctora-IQ2_XS.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 Artefact2/Proctora-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Artefact2/Proctora-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Artefact2/Proctora-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 Artefact2/Proctora-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Artefact2/Proctora-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 Artefact2/Proctora-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Artefact2/Proctora-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 Artefact2/Proctora-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Artefact2/Proctora-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Artefact2/Proctora-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Artefact2/Proctora-GGUF with Ollama:
```
ollama run hf.co/Artefact2/Proctora-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Artefact2/Proctora-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 Artefact2/Proctora-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 Artefact2/Proctora-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Artefact2/Proctora-GGUF to start chatting

Docker Model Runner
How to use Artefact2/Proctora-GGUF with Docker Model Runner:
```
docker model run hf.co/Artefact2/Proctora-GGUF:Q4_K_M
```

Lemonade

How to use Artefact2/Proctora-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Artefact2/Proctora-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Proctora-GGUF-Q4_K_M

List all available models

lemonade list

Vulkan

by KayJayEno - opened Jan 29, 2024

Discussion

KayJayEno

Jan 29, 2024

Trying Q4_K_M & Q4_K_S with Koboldcpp 1.56, I'm unable to offload any layers using Vulkan without the program exiting with an error,
llm_load_tensors: offloaded 5/33 layers to GPU
llm_load_tensors: CPU buffer size = 7000.37 MiB
llm_load_tensors: Vulkan buffer size = 1057.73 MiB
...
GGML_ASSERT: ggml-vulkan.cpp:2738: src1 == nullptr || ggml_vk_dim01_contiguous(src1)
Could not attach to process. If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Operation not permitted.
No stack.
The program is not being run.

While I am able to use Vulkan with 0 layers set in the quick launcher using Proctora-Q4_K_S/M,
I can offload 24 layers with 8192 context on llama2-13b-psyfighter.Q4_K_M, for example,
and 12 layers with 8192 context on mergemonster-13b-20231124.Q5_K_M.

Artefact2

Owner Jan 29, 2024

The vulkan backend doesn't support mixtral (or mixtral-like) models yet. Use CUDA/ROCm or OpenCL for the time being!

Karko

Feb 5, 2024

I discovered this page almost by accident.

I am very grateful for your work.

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