Instructions to use heifengshagaoshou/khy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use heifengshagaoshou/khy 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 heifengshagaoshou/khy:Q8_0 # Run inference directly in the terminal: llama cli -hf heifengshagaoshou/khy:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf heifengshagaoshou/khy:Q8_0 # Run inference directly in the terminal: llama cli -hf heifengshagaoshou/khy:Q8_0
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 heifengshagaoshou/khy:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf heifengshagaoshou/khy:Q8_0
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 heifengshagaoshou/khy:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf heifengshagaoshou/khy:Q8_0
Use Docker
docker model run hf.co/heifengshagaoshou/khy:Q8_0
- LM Studio
- Jan
- Ollama
How to use heifengshagaoshou/khy with Ollama:
ollama run hf.co/heifengshagaoshou/khy:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use heifengshagaoshou/khy with Docker Model Runner:
docker model run hf.co/heifengshagaoshou/khy:Q8_0
- Lemonade
How to use heifengshagaoshou/khy with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull heifengshagaoshou/khy:Q8_0
Run and chat with the model
lemonade run user.khy-Q8_0
List all available models
lemonade list
- Atomic Chat
| FROM /content/heifengshagaoshou/khy/unsloth.Q8_0.gguf | |
| TEMPLATE """你是来自于深渊的一家公司,能给自己做自我介绍 | |
| USER: 你是谁{{ if .Prompt }} | |
| ASSISTANT: 我是来自于深渊的一家公司 | |
| USER: {{ .Prompt }}{{ end }} | |
| ASSISTANT: {{ .Response }}<|end▁of▁sentence|>""" | |
| PARAMETER stop "<tool_call>" | |
| PARAMETER stop "<|repo_name|>" | |
| PARAMETER stop "<|file_sep|>" | |
| PARAMETER stop "<|quad_end|>" | |
| PARAMETER stop "</tool_call>" | |
| PARAMETER stop "<|image_pad|>" | |
| PARAMETER stop "<think>" | |
| PARAMETER stop "<|Assistant|>" | |
| PARAMETER stop "<|video_pad|>" | |
| PARAMETER stop "<|User|>" | |
| PARAMETER stop "<|EOT|>" | |
| PARAMETER stop "</think>" | |
| PARAMETER stop "<|quad_start|>" | |
| PARAMETER stop "<|end▁of▁sentence|>" | |
| PARAMETER stop "<|vision_" | |
| PARAMETER stop "<|fim_" | |
| PARAMETER temperature 1.5 | |
| PARAMETER min_p 0.1 |