Instructions to use tony65535/llavon-ime-llama-250m-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tony65535/llavon-ime-llama-250m-GGUF with 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 tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tony65535/llavon-ime-llama-250m-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 tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tony65535/llavon-ime-llama-250m-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 tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use tony65535/llavon-ime-llama-250m-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tony65535/llavon-ime-llama-250m-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tony65535/llavon-ime-llama-250m-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M

Ollama
How to use tony65535/llavon-ime-llama-250m-GGUF with Ollama:
```
ollama run hf.co/tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use tony65535/llavon-ime-llama-250m-GGUF with Docker Model Runner:
```
docker model run hf.co/tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M
```

Lemonade

How to use tony65535/llavon-ime-llama-250m-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tony65535/llavon-ime-llama-250m-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.llavon-ime-llama-250m-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

拉風輸入法（Llavon IME）LLaMA 250M GGUF

GGUF builds for tony65535/llavon-ime-llama-250m.

This model is a small decoder-only LLaMA-style model trained for Traditional Chinese Bopomofo IME conversion.

Project source code and IME implementations for Windows, macOS, and Linux: 拉風輸入法（Llavon IME）on GitHub.

Files

File	Notes
`llavon-ime-llama-250m-Q4_K_M.gguf`	Recommended deployment build
`llavon-ime-llama-250m-Q3_K_M.gguf`	Smaller experimental build
`llavon-ime-llama-250m-IQ3_M.gguf`	Smaller experimental build
`llavon-ime-llama-250m-Q2_K.gguf`	Smallest uploaded build; quality should be checked before use
`llavon-ime-llama-250m-f16.gguf`	F16 reference build

Inference Notes

This is not a general chat model. It is intended for IME-style inference with a custom Bopomofo vocabulary.

Typical inference format:

<BOS> <context-char-0> <context-char-1> ... <Bopomofo-0> <Bopomofo-1> ... <SEP> <char-0> <char-1> ...

The context characters before the Bopomofo tokens are optional already-entered Traditional Chinese text. During IME inference, logits should be masked to the legal candidate character set for the current Bopomofo syllable.

License

The GGUF weights are released under CC-BY-NC-4.0.

The model weights were independently trained by this project. We do not take the position that model weights are necessarily reproductions, adaptations, or derivative works of the training datasets.

However, the training process included third-party datasets marked as CC-BY-NC-4.0. As a conservative approach to the original data licenses, source-rights uncertainty, and potential copyright risk, we release the GGUF weights under CC-BY-NC-4.0 for non-commercial use only.

This licensing choice should not be interpreted as an admission that the model weights are necessarily governed by any particular training dataset license. It is a conservative release strategy adopted for risk management and open publication.

The source code for the IME runtime may be released under a separate software license.

The released model weights do not contain the original training corpora and are not intended to reproduce or redistribute the underlying training texts. This project does not grant any rights to use, copy, or redistribute the original training datasets.

See DATA_SOURCES.md for the training data statement and source summary.

Downloads last month: 1,383

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

16-bit

Model tree for tony65535/llavon-ime-llama-250m-GGUF

Base model

tony65535/llavon-ime-llama-250m

Quantized

(1)

this model