How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf afrideva/bloomz-Alpaca-560M-GGUF:
# Run inference directly in the terminal:
llama cli -hf afrideva/bloomz-Alpaca-560M-GGUF:
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf afrideva/bloomz-Alpaca-560M-GGUF:
# Run inference directly in the terminal:
llama cli -hf afrideva/bloomz-Alpaca-560M-GGUF:
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf afrideva/bloomz-Alpaca-560M-GGUF:
# Run inference directly in the terminal:
./build/bin/llama cli -hf afrideva/bloomz-Alpaca-560M-GGUF:
Use Docker
docker model run hf.co/afrideva/bloomz-Alpaca-560M-GGUF:
Quick Links

p208p2002/bloomz-Alpaca-560M-GGUF

Quantized GGUF model files for bloomz-Alpaca-560M from p208p2002

Name Quant method Size
bloomz-alpaca-560m.q2_k.gguf q2_k 430.81 MB
bloomz-alpaca-560m.q3_k_m.gguf q3_k_m 492.33 MB
bloomz-alpaca-560m.q4_k_m.gguf q4_k_m 561.16 MB
bloomz-alpaca-560m.q5_k_m.gguf q5_k_m 625.29 MB
bloomz-alpaca-560m.q6_k.gguf q6_k 682.78 MB
bloomz-alpaca-560m.q8_0.gguf q8_0 880.26 MB

Original Model Card:

Fine-Tune BLOOMZ Model on Alpaca 52K.

Downloads last month
150
GGUF
Model size
0.8B params
Architecture
bloom
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for afrideva/bloomz-Alpaca-560M-GGUF

Quantized
(3)
this model

Dataset used to train afrideva/bloomz-Alpaca-560M-GGUF