Text Generation
Safetensors
GGUF
qwen2
ternary
bitnet
1.58bit
cpu
deepseek
efficient
low-memory
jirack
web-ui
routing
tool-call
robotics
conversational
Instructions to use CMSManhattan/JiRackUltra_7b 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 CMSManhattan/JiRackUltra_7b 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 CMSManhattan/JiRackUltra_7b:Q4_K_M # Run inference directly in the terminal: llama cli -hf CMSManhattan/JiRackUltra_7b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf CMSManhattan/JiRackUltra_7b:Q4_K_M # Run inference directly in the terminal: llama cli -hf CMSManhattan/JiRackUltra_7b:Q4_K_M
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 CMSManhattan/JiRackUltra_7b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf CMSManhattan/JiRackUltra_7b:Q4_K_M
Use Docker
docker model run hf.co/CMSManhattan/JiRackUltra_7b:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use CMSManhattan/JiRackUltra_7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CMSManhattan/JiRackUltra_7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CMSManhattan/JiRackUltra_7b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/CMSManhattan/JiRackUltra_7b:Q4_K_M
- Ollama
How to use CMSManhattan/JiRackUltra_7b with Ollama:
ollama run hf.co/CMSManhattan/JiRackUltra_7b:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use CMSManhattan/JiRackUltra_7b with Docker Model Runner:
docker model run hf.co/CMSManhattan/JiRackUltra_7b:Q4_K_M
- Lemonade
How to use CMSManhattan/JiRackUltra_7b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull CMSManhattan/JiRackUltra_7b:Q4_K_M
Run and chat with the model
lemonade run user.JiRackUltra_7b-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download JiRackUltra_7b.Q8_0.gguf from CMSManhattan/JiRackUltra_7b: direct link, hf CLI and curl.
- Browser
- Download file 8.1 GB
-
https://huggingface.co/CMSManhattan/JiRackUltra_7b/resolve/main/JiRackUltra_7b.Q8_0.gguf
- Command line
-
hf download hf://CMSManhattan/JiRackUltra_7b/JiRackUltra_7b.Q8_0.gguf
-
curl -L -o JiRackUltra_7b.Q8_0.gguf https://huggingface.co/CMSManhattan/JiRackUltra_7b/resolve/main/JiRackUltra_7b.Q8_0.gguf
8.1 GB
- Xet hash:
- 1f5488ca1a2172ae077cbfca7e11c022cbe308158614c373850e73ed3066288d
- Size of remote file:
- 8.1 GB
- SHA256:
- 99b560e048371f307ab8b59ee1666b2ce9d1cc7508b48b5c2f68755156ae353a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.