Instructions to use HuanLin/ayaka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuanLin/ayaka with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HuanLin/ayaka",
	filename="q4_0_akaya.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use HuanLin/ayaka with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HuanLin/ayaka:Q4_0_AKAYA
# Run inference directly in the terminal:
llama-cli -hf HuanLin/ayaka:Q4_0_AKAYA

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf HuanLin/ayaka:Q4_0_AKAYA
# Run inference directly in the terminal:
llama-cli -hf HuanLin/ayaka:Q4_0_AKAYA

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 HuanLin/ayaka:Q4_0_AKAYA
# Run inference directly in the terminal:
./llama-cli -hf HuanLin/ayaka:Q4_0_AKAYA

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 HuanLin/ayaka:Q4_0_AKAYA
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HuanLin/ayaka:Q4_0_AKAYA

Use Docker

docker model run hf.co/HuanLin/ayaka:Q4_0_AKAYA

LM Studio
Jan
Ollama
How to use HuanLin/ayaka with Ollama:
```
ollama run hf.co/HuanLin/ayaka:Q4_0_AKAYA
```

Unsloth Studio new

How to use HuanLin/ayaka 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 HuanLin/ayaka 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 HuanLin/ayaka to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HuanLin/ayaka to start chatting

Docker Model Runner
How to use HuanLin/ayaka with Docker Model Runner:
```
docker model run hf.co/HuanLin/ayaka:Q4_0_AKAYA
```

Lemonade

How to use HuanLin/ayaka with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HuanLin/ayaka:Q4_0_AKAYA

Run and chat with the model

lemonade run user.ayaka-Q4_0_AKAYA

List all available models

lemonade list

神里绫华 LLM 模型

Train on RTX 3090x2

Based on Qwen2-7b-Instruct

Datasets are collected by @zzc想睡觉觉觉觉觉

使用方式

下载后

ollama create akaya -f ./Modelfile
ollama run akaya

其他

除了 Q4_0 量化以外，还提供了 Q8_0 量化的模型，请自己更改配置

Downloads last month: 42

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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