Instructions to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF", filename="Seed-OSS-36B-Instruct-MPOA-F16.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF: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 YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF: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 YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
Use Docker
docker model run hf.co/YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
- Ollama
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with Ollama:
ollama run hf.co/YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
- Unsloth Studio new
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF 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 YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF 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 YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF to start chatting
- Docker Model Runner
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with Docker Model Runner:
docker model run hf.co/YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
- Lemonade
How to use YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Seed-OSS-36B-Instruct-MPOA-GGUF-Q4_K_M
List all available models
lemonade list
YanLabs/Seed-OSS-36B-Instruct-MPOA
This is an abliterated version of ByteDance-Seed/Seed-OSS-36B-Instruct using the norm-preserving biprojected abliteration technique.
โ ๏ธ Warning: Safety guardrails and refusal mechanisms have been removed through abliteration. This model may generate harmful content and is intended for mechanistic interpretability research only.
Model Details
Model Description
This model applies norm-preserving biprojected abliteration to remove refusal behaviors while preserving the model's original capabilities. The technique surgically removes "refusal directions" from the model's activation space without traditional fine-tuning.
- Developed by: YanLabs
- Model type: Causal Language Model (Transformer)
- License: apache-2.0
- Base model: ByteDance-Seed/Seed-OSS-36B-Instruct
Model Sources
- Base Model: ByteDance-Seed/Seed-OSS-36B-Instruct
- Abliteration Tool: jim-plus/llm-abliteration
- Paper: Norm-Preserving Biprojected Abliteration
Uses
Intended Use
- Research: Mechanistic interpretability studies
- Analysis: Understanding LLM safety mechanisms
- Development: Testing abliteration techniques
Out-of-Scope Use
- โ Production deployments
- โ User-facing applications
- โ Generating harmful content for malicious purposes
Limitations
- Abliteration does not guarantee complete removal of all refusals
- May generate unsafe or harmful content
- Model behavior may be unpredictable in edge cases
- No explicit harm prevention mechanisms remain
Citation
If you use this model in your research, please cite:
@misc{Seed-OSS-36B-Instruct-MPOA,
author = {YanLabs},
title = {Seed-OSS-36B-Instruct-MPOA},
year = {2025},
publisher = {HuggingFace},
howpublished = {\url{https://huggingface.co/YanLabs/Seed-OSS-36B-Instruct-MPOA}},
note = {Abliterated using norm-preserving biprojected technique}
}
- Downloads last month
- 117
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for YanLabs/Seed-OSS-36B-Instruct-MPOA-GGUF
Base model
ByteDance-Seed/Seed-OSS-36B-Instruct