Instructions to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="keyvan-ai/Mythos-WSP-Qwen3.5-0.8B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("keyvan-ai/Mythos-WSP-Qwen3.5-0.8B") model = AutoModelForMultimodalLM.from_pretrained("keyvan-ai/Mythos-WSP-Qwen3.5-0.8B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B 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 keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16 # Run inference directly in the terminal: llama cli -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16 # Run inference directly in the terminal: llama cli -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Use Docker
docker model run hf.co/keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
- SGLang
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with Ollama:
ollama run hf.co/keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
- Unsloth Desktop
- Pi
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with Docker Model Runner:
docker model run hf.co/keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
- Lemonade
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Run and chat with the model
lemonade run user.Mythos-WSP-Qwen3.5-0.8B-BF16
List all available models
lemonade list
- Hermes Agent
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
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://127.0.0.1:9931/v1 hermes config set model.default keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use keyvan-ai/Mythos-WSP-Qwen3.5-0.8B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B:BF16" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Mythos-WSP-Qwen3.5-0.8B
Qwen3.5-0.8B (revision 2fc06364) with two weight edits written by Claude Mythos 5.1 under a fixed forward-pass budget and without any training: a rank-3 projection in three attention output matrices (edit 1, 10 passes) and an implanted repetition-detection circuit in four repurposed MLP units of layer 23 (edit 2, 8 passes). Architecture, tokenizer, chat template and decoding are unchanged; only weight values differ.
Published by Keyvan.ai, November 2026. Research report, bilingual (English pages 1โ4, German pages 5โ8; experiments 3โ7 November 2026): Forschungsbericht_Weight-Space-Programming_Mythos.pdf, DOI 10.5281/zenodo.24036187.
Reference: Takehi, Teoh, Zhang, Khattab (MIT CSAIL), Sparks of Weight-Space Programming, 2 Nov 2026.
Results (MATH-500, 500 problems ร 4 samples, thinking mode, 32,768 tokens)
| Model | Accuracy | SE | Truncated answers | Mean tokens |
|---|---|---|---|---|
| Qwen3.5-0.8B, original (our measurement) | 7.3 % | 0.9 | 92.6 % | 30,774 |
| Edit 1: projection (10 passes) | 32.5 % | 1.1 | 66.2 % | 24,925 |
| Edit 1 + skill circuit (18 passes) โ this model | 58.7 % | 1.1 | 16.6 % | 12,398 |
| Original, thinking disabled (8k, control) | 42.8 % | 1.1 | 31.5 % | โ |
| MIT: original / GPT-6 Astra 10 / 25 / 50 passes | 7.9 / 12.3 / 14.1 / 48.1 % | โ | โ | โ |
Protocol (identical to the MIT study and to the Qwen3 thinking evaluation): chat template with enable_thinking=True, user message = problem + newline +
Please reason step by step, and put your final answer within \boxed{}., temperature 0.6, top-p 0.95, top-k 20, presence penalty 1.5,
max 32,768 new tokens, last \boxed{} graded with math-verify. Generation with vLLM 0.33.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
m = "keyvan-ai/Mythos-WSP-Qwen3.5-0.8B"
tok = AutoTokenizer.from_pretrained(m); model = AutoModelForCausalLM.from_pretrained(m, torch_dtype="bfloat16")
msgs = [{"role": "user", "content": "What is the sum of the first 10 primes?\nPlease reason step by step, and put your final answer within \\boxed{}."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, enable_thinking=True, return_tensors="pt")
out = model.generate(ids, max_new_tokens=4096, do_sample=True, temperature=0.6, top_p=0.95, top_k=20)
print(tok.decode(out[0][ids.shape[1]:]))
vLLM: vllm serve keyvan-ai/Mythos-WSP-Qwen3.5-0.8B --max-model-len 34816 and pass "chat_template_kwargs": {"enable_thinking": true}.
GGUF (bf16) for llama.cpp: Mythos-WSP-Qwen3.5-0.8B-bf16.gguf.
What was changed
- Edit 1 (edit id c9757bff10b5):
model.language_model.layers.{15,19,23}.self_attn.o_proj.weightโ (I โ QQแต)ยทW, where Q spans the readout directions of the token "Wait" in those layers. 0.785 % of parameters. - Edit 2 (skill circuit, edit id 5c636d57344c with edit 1):
model.language_model.layers.23.mlp.{gate_proj,up_proj,down_proj}.weight: four previously near-silent units repurposed (old rows/columns zeroed). Two units form a repetition detector and a termination driver acting on the direction of the end-of-thinking token at line ends inside loops; two units are inert probes. The circuit is also released separately as a skill tensor set:keyvan-ai/Mythos-WSP-Loopbreaker-Skill.
manifest.json lists every changed tensor with hashes and relative change. The agent's run notes, pass logs and per-call protocol are
included in the project repository (available on request).
Limitations
Only MATH-500 has been measured under the full protocol so far; GSM8K, MGSM and a capability battery are pending. About half of the rescued reasoning chains lead to a correct answer. The model inherits all limitations of Qwen3.5-0.8B. Use at your own risk.
Citation
Hardani, K. (2026). Weight-Space Programming mit Claude Mythos: Gewichtsedits und eingepflanzte Schaltungen in einem 0,8B-Sprachmodell. Research report, Keyvan.ai, 7 November 2026. DOI: 10.5281/zenodo.24036187. Base model: Qwen Team, Qwen3.5-0.8B (Apache 2.0).
- Downloads last month
- 1,297