Instructions to use akx/Poro-34B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use akx/Poro-34B-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="akx/Poro-34B-gguf",
	filename="ggml-model-Q3_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 akx/Poro-34B-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf akx/Poro-34B-gguf
# Run inference directly in the terminal:
llama-cli -hf akx/Poro-34B-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf akx/Poro-34B-gguf
# Run inference directly in the terminal:
llama-cli -hf akx/Poro-34B-gguf

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 akx/Poro-34B-gguf
# Run inference directly in the terminal:
./llama-cli -hf akx/Poro-34B-gguf

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 akx/Poro-34B-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf akx/Poro-34B-gguf

Use Docker

docker model run hf.co/akx/Poro-34B-gguf

LM Studio
Jan
Ollama
How to use akx/Poro-34B-gguf with Ollama:
```
ollama run hf.co/akx/Poro-34B-gguf
```

Unsloth Studio new

How to use akx/Poro-34B-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 akx/Poro-34B-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 akx/Poro-34B-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for akx/Poro-34B-gguf to start chatting

Docker Model Runner
How to use akx/Poro-34B-gguf with Docker Model Runner:
```
docker model run hf.co/akx/Poro-34B-gguf
```

Lemonade

How to use akx/Poro-34B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull akx/Poro-34B-gguf

Run and chat with the model

lemonade run user.Poro-34B-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Poro-34B-gguf

This is a GGUF quantization of the Poro-34B model.

Please refer to that repository's model card for details.

The current revision is a quantization of the 1000B token checkpoint.

The conversion was done with llama.cpp version b2354 (e25fb4b18fcedb9bed6be4585cf842e9a669b28b) on a Google Compute machine generously sponsored by Valohai.

Downloads last month: 28

GGUF

Model size

35B params

Architecture

bloom

Hardware compatibility

Inference Providers NEW

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