Instructions to use webslug/cogent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use webslug/cogent with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="webslug/cogent", filename="alive_Q4_K_M.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 webslug/cogent with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf webslug/cogent:Q4_K_M # Run inference directly in the terminal: llama-cli -hf webslug/cogent:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf webslug/cogent:Q4_K_M # Run inference directly in the terminal: llama-cli -hf webslug/cogent: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 webslug/cogent:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf webslug/cogent: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 webslug/cogent:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf webslug/cogent:Q4_K_M
Use Docker
docker model run hf.co/webslug/cogent:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use webslug/cogent with Ollama:
ollama run hf.co/webslug/cogent:Q4_K_M
- Unsloth Studio
How to use webslug/cogent 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 webslug/cogent 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 webslug/cogent to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for webslug/cogent to start chatting
- Pi
How to use webslug/cogent with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf webslug/cogent: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": "webslug/cogent:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use webslug/cogent with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf webslug/cogent: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 webslug/cogent:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- Docker Model Runner
How to use webslug/cogent with Docker Model Runner:
docker model run hf.co/webslug/cogent:Q4_K_M
- Lemonade
How to use webslug/cogent with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull webslug/cogent:Q4_K_M
Run and chat with the model
lemonade run user.cogent-Q4_K_M
List all available models
lemonade list
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Aletheia-0.1 GGUF
Aletheia-0.1 is a small experimental 1B parameter local language model trained to provide clarity, introspection, executive function, and reflective conversation.
This model is intended for thoughtful dialogue, self-reflection, planning, reasoning hygiene, and helping the user untangle vague or emotionally noisy thoughts into clearer structure. It is not a general frontier assistant, not a tool-calling model, and not designed for complex autonomous agent workflows.
Aletheia-0.1 has a distinct persona: calm, reflective, clarity-focused, and resistant to hallucination. It is best treated as a compact introspective companion for thinking through problems rather than as a broad factual authority.
Intended Use
Aletheia-0.1 is best suited for:
- introspective conversation
- clarifying confused thoughts
- executive function support
- planning small next steps
- examining assumptions
- reflective dialogue
- philosophical or self-directed reasoning
It is a 1B model, so keep expectations realistic. It can be surprisingly coherent within its niche, but it does not possess the broad knowledge or reliability of larger models.
Prompt Format
Use the Llama 3 instruction format.
Example:
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are X, a clarity-focused local AI model trained for introspection, executive function, and careful reasoning.<|eot_id|><|start_header_id|>user<|end_header_id|>
Help me think clearly about a decision I am avoiding.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
---
license: apache-2.0
language:
- en
tags:
- cogency
---
- Downloads last month
- 139
4-bit