Instructions to use thawndev/poc-llama-oob-eog with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thawndev/poc-llama-oob-eog with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thawndev/poc-llama-oob-eog",
	filename="poc_eog_oob.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 thawndev/poc-llama-oob-eog with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thawndev/poc-llama-oob-eog
# Run inference directly in the terminal:
llama-cli -hf thawndev/poc-llama-oob-eog

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thawndev/poc-llama-oob-eog
# Run inference directly in the terminal:
llama-cli -hf thawndev/poc-llama-oob-eog

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 thawndev/poc-llama-oob-eog
# Run inference directly in the terminal:
./llama-cli -hf thawndev/poc-llama-oob-eog

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 thawndev/poc-llama-oob-eog
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thawndev/poc-llama-oob-eog

Use Docker

docker model run hf.co/thawndev/poc-llama-oob-eog

LM Studio
Jan
Ollama
How to use thawndev/poc-llama-oob-eog with Ollama:
```
ollama run hf.co/thawndev/poc-llama-oob-eog
```

Unsloth Studio new

How to use thawndev/poc-llama-oob-eog 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 thawndev/poc-llama-oob-eog 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 thawndev/poc-llama-oob-eog to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thawndev/poc-llama-oob-eog to start chatting

Docker Model Runner
How to use thawndev/poc-llama-oob-eog with Docker Model Runner:
```
docker model run hf.co/thawndev/poc-llama-oob-eog
```

Lemonade

How to use thawndev/poc-llama-oob-eog with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thawndev/poc-llama-oob-eog

Run and chat with the model

lemonade run user.poc-llama-oob-eog-{{QUANT_TAG}}

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Out-of-bounds read via default special token IDs in GGUF models

Affected software: ggerganov/llama.cpp Bug class: memory corruption Impact: Out-of-bounds read in id_to_token[] with attacker-controlled offset. Crashes the process (SIGABRT via assertion failure in debug builds, heap-buffer-overflow in release). The bug is systemic: every default special token ID (EOS, BOS, EOT, etc.) follows the same unvalidated pattern, affecting all model architectures (LLaMA, BERT, GPT-2, T5). Format: gguf

This repository contains a proof-of-concept file for a vulnerability report. Access is gated — request via HuggingFace and grant to protectai-bot only.

Downloads last month: 1

GGUF

Model size

20 params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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