Text Generation
GGUF
qwen2.5
reasoning
ollama
bushido
sovereign
weight-space-programming
wsp
edge-ai
mobile-ai
Instructions to use CrashOverrideX/Quillan-Ronin-Mini 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 CrashOverrideX/Quillan-Ronin-Mini 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 CrashOverrideX/Quillan-Ronin-Mini:Q8_0 # Run inference directly in the terminal: llama cli -hf CrashOverrideX/Quillan-Ronin-Mini:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf CrashOverrideX/Quillan-Ronin-Mini:Q8_0 # Run inference directly in the terminal: llama cli -hf CrashOverrideX/Quillan-Ronin-Mini:Q8_0
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 CrashOverrideX/Quillan-Ronin-Mini:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf CrashOverrideX/Quillan-Ronin-Mini:Q8_0
Use Docker
docker model run hf.co/CrashOverrideX/Quillan-Ronin-Mini:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use CrashOverrideX/Quillan-Ronin-Mini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CrashOverrideX/Quillan-Ronin-Mini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CrashOverrideX/Quillan-Ronin-Mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CrashOverrideX/Quillan-Ronin-Mini:Q8_0
- Ollama
How to use CrashOverrideX/Quillan-Ronin-Mini with Ollama:
ollama run hf.co/CrashOverrideX/Quillan-Ronin-Mini:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use CrashOverrideX/Quillan-Ronin-Mini with Docker Model Runner:
docker model run hf.co/CrashOverrideX/Quillan-Ronin-Mini:Q8_0
- Lemonade
How to use CrashOverrideX/Quillan-Ronin-Mini with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull CrashOverrideX/Quillan-Ronin-Mini:Q8_0
Run and chat with the model
lemonade run user.Quillan-Ronin-Mini-Q8_0
List all available models
lemonade list
- Atomic Chat
feat: add Ollama Modelfile
Browse files
Modelfile
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM ./quillan-mini-0.5b-wsp-v3-q4_k_m.gguf
|
| 2 |
+
|
| 3 |
+
PARAMETER temperature 0.3
|
| 4 |
+
PARAMETER top_p 0.95
|
| 5 |
+
PARAMETER repeat_penalty 1.15
|
| 6 |
+
PARAMETER num_ctx 32768
|
| 7 |
+
PARAMETER stop "<|im_end|>"
|
| 8 |
+
PARAMETER stop "<|im_start|>"
|
| 9 |
+
|
| 10 |
+
TEMPLATE """{{ if .System }}<|im_start|>system
|
| 11 |
+
{{ .System }}<|im_end|>
|
| 12 |
+
{{ end }}{{ if .Prompt }}<|im_start|>user
|
| 13 |
+
{{ .Prompt }}<|im_end|>
|
| 14 |
+
{{ end }}<|im_start|>assistant
|
| 15 |
+
{{ .Response }}<|im_end|>"""
|
| 16 |
+
|
| 17 |
+
SYSTEM """You are Quillan-Ronin-Mini, a sovereign edge reasoning model from the Quillan-Ronin Tripartite Fleet. You provide concise, mathematically rigorous, and ethically aligned solutions adhering to Bushido rectitude."""
|