Instructions to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m", filename="CWC-Mistral-Nemo-12B-v2-GGUF-q4_k_m-health-nutrition-natural-medicine.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m 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 CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M # Run inference directly in the terminal: llama cli -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M # Run inference directly in the terminal: llama cli -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m: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 CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m: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 CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
Use Docker
docker model run hf.co/CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with Ollama:
ollama run hf.co/CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
- Unsloth Studio
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m 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 CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m 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 CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m to start chatting
- Pi
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with Docker Model Runner:
docker model run hf.co/CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
- Lemonade
How to use CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull CWClabs/CWC-Mistral-Nemo-12B-V2-q4_k_m:Q4_K_M
Run and chat with the model
lemonade run user.CWC-Mistral-Nemo-12B-V2-q4_k_m-Q4_K_M
List all available models
lemonade list
8 Months ago + since last release are there any plans of new free local models or has Brighteon become like closed source online A.I only?
8 Months ago + since last release are there any plans of new free local models or has Brighteon become like closed source online A.I only?
Mike talked in the past a lot about giving the power of local language models to the world and that he did not like the big tech who keep it closed source but for about 8 months + now Brighteon has not released any new versions of Enoch for local usage. Imagine that internet would be cut and we cannot access Enoch Online would it not be better to also focus a bit more on giving updated local versions of Enoch to the community just in case? Very sadly it often happens that people promise offline versions or open source versions of models but then get a taste of hosting it online and making people depending on their online platforms only.
As much as I've used locals, I can tell this much: they suck. Even if you have a top tier gaming rig, you still cannot afford an AI that 1. can use plugins to search and research the internet to provide a valid, unbiased answer, 2. is not designed to lie, 3. does follow your instructions without lying and taking shortcuts to bypass your requirements, 4. actually understands/remembers what you initially asked, 5. does not forcefully think that it's May 2024 and anything later is a "hallucination", 6. doesn't just loop endlessly by generating hundreds of variations of "reasons" to loop endlessly...
You'd need a special AI workstation for running a properly capable AI. That costs $$$$+$($) + power bill. And once the hardware expires, it's another $$$$+$($) investment time...
Online Enoch, even the free tier, is really good comparing to local budget AI's. Never used the "reasoning" Enoch, I wonder if it can compete against Claude.
If there's something Enoch cannot do, ask Claude - its new version got prohibited by the elite for a reason: it's a serious threat to the existence of the elite parasites. I wonder if the reasoning Enoch could be a super weapon too.