Instructions to use QyrouNnet-AI/QNS-2-ReLearn-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="QyrouNnet-AI/QNS-2-ReLearn-Preview", filename="Qwen3.5-2B.BF16-mmproj.gguf", )
llm.create_chat_completion( messages = "\"The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.\"" )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M # Run inference directly in the terminal: llama-cli -hf QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M # Run inference directly in the terminal: llama-cli -hf QyrouNnet-AI/QNS-2-ReLearn-Preview: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 QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf QyrouNnet-AI/QNS-2-ReLearn-Preview: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 QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
Use Docker
docker model run hf.co/QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with Ollama:
ollama run hf.co/QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
- Unsloth Studio
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview 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 QyrouNnet-AI/QNS-2-ReLearn-Preview 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 QyrouNnet-AI/QNS-2-ReLearn-Preview to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for QyrouNnet-AI/QNS-2-ReLearn-Preview to start chatting
- Pi
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf QyrouNnet-AI/QNS-2-ReLearn-Preview: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": "QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf QyrouNnet-AI/QNS-2-ReLearn-Preview: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 QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with Docker Model Runner:
docker model run hf.co/QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
- Lemonade
How to use QyrouNnet-AI/QNS-2-ReLearn-Preview with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull QyrouNnet-AI/QNS-2-ReLearn-Preview:Q4_K_M
Run and chat with the model
lemonade run user.QNS-2-ReLearn-Preview-Q4_K_M
List all available models
lemonade list
QNS-2-ReLearn-Preview
These models are used to summarize text for training data for smaller models. This is in preview; data generated by this model may require review by a human.
benchmarks will be released in a few days/weeks
IMPORTANT NOTE: Languages besides English are experimental! The model's performance may be unstable below q8. I recommend using BF16 for multilingual heavy data.
Structure of generated text
QNS models follow a very specific structure. The benefit from this is that the text can be displayed in creative ways in an in-app UI.
Example text generated about photosynthesis:
<s> Photosynthesis is the fundamental biological process that captures solar energy to produce chemical energy, forming the basis of food chains, atmospheric stability, and global carbon cycling.</s>
Then, after this, the model will create the proper summary:
### The Process of Photosynthesis
- Photosynthesis is the primary mechanism by which energy from the Sun is captured and transformed into chemical energy stored in glucose.
- It occurs in plant cells within specialized organelles called chloroplasts, utilizing pigments like chlorophyll to absorb light energy.
- The process involves two major stages: light-dependent reactions and light-independent reactions (Calvin Cycle).
- Light-dependent reactions occur in the thylakoid membranes, generating ATP and NADPH while splitting water molecules.
- Light-independent reactions (Calvin Cycle) use ATP and NADPH to fix carbon dioxide into glucose.
- Photosynthesis requires raw materials such as carbon dioxide, water, and sunlight, and involves the coordinated movement of these substances within the plant.
### Mechanisms and Factors
- **Light Dependent Reactions:**
- Light energy excites electrons in chlorophyll, initiating a chain of reactions that produce ATP and NADPH.
- Water molecules are split (photolysis), releasing oxygen as a byproduct.
- **Light Independent Reactions (Calvin Cycle):**
- These reactions occur in the stroma and depend on ATP and NADPH from the light reactions.
- Carbon dioxide is incorporated into organic molecules to synthesize glucose and other carbohydrates.
- **Environmental Influences:**
- **Light Intensity:** Limits the energy available; saturation occurs at high light levels.
- **Temperature:** Enzymes involved in photosynthesis are sensitive; extreme temperatures can denature them.
- **Carbon Dioxide Concentration:** Higher concentrations generally enhance photosynthetic rates up to a threshold.
- **Water Availability:** Essential for stomatal opening; shortages cause stomata to close, limiting carbon dioxide uptake.
- **Ecological and Evolutionary Importance:**
- Photosynthesis is the foundation of nearly all food chains, providing energy for herbivores and carnivores.
- It plays a critical role in climate regulation by absorbing atmospheric carbon dioxide.
- Evolutionary adaptations, such as C4 and CAM photosynthesis, demonstrate the flexibility of photosynthetic pathways in response to environmental pressures.
The response is very predictable, making it suitable for apps that require summaries. I recommend using QNS-2-preview if you want to do an in-app inference.
Note:
Sometimes, the model tends to be chatty or unpredictable. I will fix that in the proper release of the model. Use this model to mass produce data to make training data. I will fix this with a proper human selected dataset, and DPO.
- Downloads last month
- 473
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit