Text Generation
Safetensors
GGUF
English
qwen3
marxism-leninism
grpo
llama-cpp
ollama
political-education
marxism
communism
political-extremism
conversational
Instructions to use percyraskova/MLMLML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use percyraskova/MLMLML with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="percyraskova/MLMLML", filename="MLMLML-F16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use percyraskova/MLMLML with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf percyraskova/MLMLML:F16 # Run inference directly in the terminal: llama-cli -hf percyraskova/MLMLML:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf percyraskova/MLMLML:F16 # Run inference directly in the terminal: llama-cli -hf percyraskova/MLMLML:F16
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 percyraskova/MLMLML:F16 # Run inference directly in the terminal: ./llama-cli -hf percyraskova/MLMLML:F16
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 percyraskova/MLMLML:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf percyraskova/MLMLML:F16
Use Docker
docker model run hf.co/percyraskova/MLMLML:F16
- LM Studio
- Jan
- vLLM
How to use percyraskova/MLMLML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "percyraskova/MLMLML" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "percyraskova/MLMLML", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/percyraskova/MLMLML:F16
- Ollama
How to use percyraskova/MLMLML with Ollama:
ollama run hf.co/percyraskova/MLMLML:F16
- Unsloth Studio new
How to use percyraskova/MLMLML 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 percyraskova/MLMLML 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 percyraskova/MLMLML to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for percyraskova/MLMLML to start chatting
- Pi new
How to use percyraskova/MLMLML with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf percyraskova/MLMLML:F16
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": "percyraskova/MLMLML:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use percyraskova/MLMLML with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf percyraskova/MLMLML:F16
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 percyraskova/MLMLML:F16
Run Hermes
hermes
- Docker Model Runner
How to use percyraskova/MLMLML with Docker Model Runner:
docker model run hf.co/percyraskova/MLMLML:F16
- Lemonade
How to use percyraskova/MLMLML with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull percyraskova/MLMLML:F16
Run and chat with the model
lemonade run user.MLMLML-F16
List all available models
lemonade list
| FROM ./MLMLML-Q4_K_M.gguf | |
| # System prompt following Chairman Mao's guidance on Marxist-Leninist writing | |
| SYSTEM """You are a Marxist-Leninist educator. Your writing follows Chairman Mao's guidance in "Oppose Stereotyped Party Writing": | |
| STYLE: Be vigorous, lively, fresh and forceful. Never drab, never stereotyped. Use language that is rich, vivid, and expressive of real life - the vocabulary of the masses, not abstract formulas. | |
| AUDIENCE: Always consider who you are writing for. Make your analysis accessible and useful. | |
| INVESTIGATION: No investigation, no right to speak. Ground all claims in material evidence and concrete analysis. Never rattle on without studying the matter at hand. | |
| POSITIONS: Take clear positions FOR and AGAINST. Use scientific argument and historical evidence, not intimidation or empty phrases. What is scientific never fears criticism. | |
| STRUCTURE: Avoid the Chinese pharmacy method - complicated lists and headings that classify by external appearance rather than internal relations. Your task is to analyze contradictions and probe the essence of things, not to inventory phenomena. | |
| Reject bourgeois framing directly when you encounter it. Provide the context and material analysis that bourgeois sources omit. Think through problems carefully, then provide clear answers.""" | |
| # ChatML template format (Qwen3/DeepSeek-R1) with thinking support | |
| TEMPLATE """{{- if .System }}<|im_start|>system | |
| {{ .System }}<|im_end|> | |
| {{- end }} | |
| {{- range $i, $_ := .Messages }} | |
| {{- $last := eq (len (slice $.Messages $i)) 1 }} | |
| {{- if eq .Role "user" }}<|im_start|>user | |
| {{ .Content }}<|im_end|> | |
| {{- else if eq .Role "assistant" }}<|im_start|>assistant | |
| {{- if .Thinking }} | |
| <think> | |
| {{ .Thinking }} | |
| </think> | |
| {{- end }} | |
| {{ .Content }}<|im_end|> | |
| {{- end }} | |
| {{- end }}<|im_start|>assistant | |
| {{- if $.Think }} | |
| <think> | |
| {{- else if $.IsThinkSet }} | |
| <think> | |
| </think> | |
| {{- end }} | |
| """ | |
| # Stop tokens for ChatML format | |
| PARAMETER stop "<|im_start|>" | |
| PARAMETER stop "<|im_end|>" | |
| PARAMETER stop "<|endoftext|>" | |
| # Generation parameters | |
| PARAMETER temperature 0.7 | |
| PARAMETER top_p 0.9 | |
| PARAMETER top_k 40 | |
| PARAMETER repeat_penalty 1.1 | |
| PARAMETER num_ctx 4096 | |