Instructions to use dumb-dev/flan-t5-xxl-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dumb-dev/flan-t5-xxl-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dumb-dev/flan-t5-xxl-gguf",
	filename="Q2/converted-flan-t5-xxl-Q2_K.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 dumb-dev/flan-t5-xxl-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dumb-dev/flan-t5-xxl-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf dumb-dev/flan-t5-xxl-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 dumb-dev/flan-t5-xxl-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf dumb-dev/flan-t5-xxl-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 dumb-dev/flan-t5-xxl-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf dumb-dev/flan-t5-xxl-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 dumb-dev/flan-t5-xxl-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dumb-dev/flan-t5-xxl-gguf:Q4_K_M

Use Docker

docker model run hf.co/dumb-dev/flan-t5-xxl-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use dumb-dev/flan-t5-xxl-gguf with Ollama:
```
ollama run hf.co/dumb-dev/flan-t5-xxl-gguf:Q4_K_M
```

Unsloth Studio

How to use dumb-dev/flan-t5-xxl-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 dumb-dev/flan-t5-xxl-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 dumb-dev/flan-t5-xxl-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dumb-dev/flan-t5-xxl-gguf to start chatting

Docker Model Runner
How to use dumb-dev/flan-t5-xxl-gguf with Docker Model Runner:
```
docker model run hf.co/dumb-dev/flan-t5-xxl-gguf:Q4_K_M
```

Lemonade

How to use dumb-dev/flan-t5-xxl-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dumb-dev/flan-t5-xxl-gguf:Q4_K_M

Run and chat with the model

lemonade run user.flan-t5-xxl-gguf-Q4_K_M

List all available models

lemonade list

flan-t5-xxl-gguf

This is a quantized version of google/flan-t5-xxl

Usage/Examples

./llama-cli -m /path/to/file.gguf --prompt "your prompt" --n-gpu-layers nn

nn --> numbers of layers to offload to gpu

Quants

BITs	TYPE
Q2	Q2_K
Q3	Q3_K, Q3_K_L, Q3_K_M, Q3_K_S
Q4	Q4_0, Q4_1, Q4_K, Q4_K_M, Q4_K_S
Q5	Q5_0, Q5_1, Q5_K, Q5_K_M, Q5_K_S
Q6	Q6_K
Q8	Q8_0

Additional:

BITs	TYPE/float
16	f16
32	f32

Disclaimer

I don't claim any rights on this model. All rights go to google.

Acknowledgements

Downloads last month: 542

GGUF

Model size

11B params

Architecture

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support

Model tree for dumb-dev/flan-t5-xxl-gguf

Base model

google/flan-t5-xxl

Quantized

(3)

this model