How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_M# Run inference directly in the terminal:
llama cli -hf mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_MUse 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 mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_MBuild 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 mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_MUse Docker
docker model run hf.co/mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_MQuick Links
Uta Sensei Tiny Aya (Q4_K_M-GGUF)
Task-specific Uta Sensei fine-tune of CohereLabs/tiny-aya-global for Japanese lyric lesson
annotation and grounded tutoring. Training run: 20260614T202728Z-full.
The model inherits Tiny Aya Global's CC-BY-NC 4.0 license and acceptable-use requirements. See the Uta Sensei repository for dataset design, benchmark results, and training configuration.
Converted with llama.cpp commit 5f04dc7ac3f40271f60105574be0f617887195bb.
- Downloads last month
- 14
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_M# Run inference directly in the terminal: llama cli -hf mclpio/uta-sensei-tiny-aya-GGUF:Q4_K_M