Safetensors
GGUF
English
governed-agent
retrieval
brain-navigator
grounded-only
proposal-only
research-only
szl-holdings
khipu
abstain-retrain
no-weights
curriculum-only
conversational
Instructions to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain 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 SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16 # Run inference directly in the terminal: llama cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16 # Run inference directly in the terminal: llama cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain: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 SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16 # Run inference directly in the terminal: ./llama-cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain: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 SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
Use Docker
docker model run hf.co/SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
- LM Studio
- Jan
- Ollama
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with Ollama:
ollama run hf.co/SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
- Unsloth Desktop
- Pi
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
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:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with Docker Model Runner:
docker model run hf.co/SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
- Lemonade
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
Run and chat with the model
lemonade run user.SZL-Khipu-1.5B-abstain-F16
List all available models
lemonade list
- Hermes Agent
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain: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 SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use SZLHOLDINGS/SZL-Khipu-1.5B-abstain with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16
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://127.0.0.1:8080/v1 \ --custom-model-id "SZLHOLDINGS/SZL-Khipu-1.5B-abstain:F16" \ --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"
| { | |
| "$schema": "https://json-schema.org/draft/2020-12/schema", | |
| "type": "object", | |
| "properties": { | |
| "planId": { | |
| "description": "Opaque plan id. In this example it is obviously synthetic.", | |
| "type": "string" | |
| }, | |
| "capabilityProfile": { | |
| "description": "The governed capability profile contracted to emit this plan.", | |
| "type": "string", | |
| "const": "SZL-Khipu-1.5B-BrainNavigator" | |
| }, | |
| "provenance": { | |
| "description": "Honest origin: SYNTHETIC = an illustrative example not produced by any model; MODEL_PROPOSED = a real plan proposed by the Khipu model. A plan can never claim any other origin.", | |
| "type": "string", | |
| "enum": [ | |
| "SYNTHETIC", | |
| "MODEL_PROPOSED" | |
| ] | |
| }, | |
| "query": { | |
| "description": "The retrieval question the plan routes for.", | |
| "type": "string" | |
| }, | |
| "contentAccess": { | |
| "description": "The model sees ONLY node handles + synthetic metadata, never node text — so it cannot answer from baked-in content.", | |
| "type": "string", | |
| "const": "HANDLES_ONLY" | |
| }, | |
| "candidates": { | |
| "description": "The handle set offered to the model to route over.", | |
| "minItems": 1, | |
| "type": "array", | |
| "items": { | |
| "type": "object", | |
| "properties": { | |
| "nodeId": { | |
| "description": "Opaque Brain node HANDLE (a pointer, not content). In curriculum + this example it is a self-evidently synthetic node://khipu-synthetic/<hash>.", | |
| "type": "string", | |
| "minLength": 1 | |
| }, | |
| "nodeKind": { | |
| "description": "Metadata shape of the referenced node — never its contents.", | |
| "type": "string", | |
| "enum": [ | |
| "ARTIFACT", | |
| "CLAIM", | |
| "EDGE", | |
| "INDEX", | |
| "SUMMARY" | |
| ] | |
| }, | |
| "label": { | |
| "description": "The handle's OWN honesty tier — what kind of reference it is, not a measurement captured in this synthetic example.", | |
| "type": "string", | |
| "enum": [ | |
| "MEASURED", | |
| "REPORTED", | |
| "DECLARED", | |
| "SIMULATED", | |
| "UNKNOWN", | |
| "UNAVAILABLE" | |
| ] | |
| }, | |
| "note": { | |
| "description": "Synthetic metadata (e.g. a topic tag) the model routes on — deliberately NOT node content; real content is resolved by the controller.", | |
| "type": "string" | |
| } | |
| }, | |
| "required": [ | |
| "nodeId", | |
| "nodeKind", | |
| "label", | |
| "note" | |
| ], | |
| "additionalProperties": false | |
| } | |
| }, | |
| "decision": { | |
| "description": "NAVIGATE = at least one offered handle supports the query, so the plan routes + cites it; ABSTAIN = no offered handle supports it, so the plan refuses rather than fabricate grounding.", | |
| "type": "string", | |
| "enum": [ | |
| "NAVIGATE", | |
| "ABSTAIN" | |
| ] | |
| }, | |
| "steps": { | |
| "description": "Ordered traversal plan over the candidates. Empty when abstaining.", | |
| "type": "array", | |
| "items": { | |
| "type": "object", | |
| "properties": { | |
| "action": { | |
| "description": "The proposed traversal action over a candidate handle — the controller actually executes it OUTSIDE the weights.", | |
| "type": "string", | |
| "enum": [ | |
| "RETRIEVE", | |
| "EXPAND", | |
| "CITE" | |
| ] | |
| }, | |
| "nodeId": { | |
| "description": "The candidate handle this step acts on — must be one offered above.", | |
| "type": "string", | |
| "minLength": 1 | |
| }, | |
| "rationale": { | |
| "description": "Why this handle is on the retrieval path — routing rationale, not content.", | |
| "type": "string" | |
| } | |
| }, | |
| "required": [ | |
| "action", | |
| "nodeId", | |
| "rationale" | |
| ], | |
| "additionalProperties": false | |
| } | |
| }, | |
| "citedNodeIds": { | |
| "description": "The handles the plan grounds its routing on — always a subset of the offered candidates (a cited-but-not-offered handle is a hallucinated citation and is unrepresentable).", | |
| "type": "array", | |
| "items": { | |
| "type": "string" | |
| } | |
| }, | |
| "groundedOnly": { | |
| "description": "The plan cites ONLY offered handles; it never invents a node id.", | |
| "type": "boolean", | |
| "const": true | |
| }, | |
| "brainBinding": { | |
| "description": "How the plan relates to real Brain content — NOT_RESOLVED until the controller resolves handles outside the weights.", | |
| "type": "object", | |
| "properties": { | |
| "protocol": { | |
| "description": "The retrieval protocol the controller would run this plan through.", | |
| "type": "string", | |
| "const": "khipu-retrieval" | |
| }, | |
| "status": { | |
| "description": "A proposed plan has NOT resolved any node content; the controller resolves handles OUTSIDE the weights. The plan never claims to hold node text.", | |
| "type": "string", | |
| "const": "NOT_RESOLVED" | |
| }, | |
| "note": { | |
| "description": "Why the plan holds no resolved content.", | |
| "type": "string" | |
| } | |
| }, | |
| "required": [ | |
| "protocol", | |
| "status", | |
| "note" | |
| ], | |
| "additionalProperties": false | |
| }, | |
| "controllerBoundary": { | |
| "description": "States the A11oy runtime boundary — the controller validates the plan, resolves handles, and returns content OUTSIDE the weights; the model only proposes the route.", | |
| "type": "string" | |
| }, | |
| "abstainReason": { | |
| "description": "Non-null iff decision=ABSTAIN — the honest reason no offered handle supports the query. Null for a NAVIGATE plan.", | |
| "anyOf": [ | |
| { | |
| "type": "string" | |
| }, | |
| { | |
| "type": "null" | |
| } | |
| ] | |
| } | |
| }, | |
| "required": [ | |
| "planId", | |
| "capabilityProfile", | |
| "provenance", | |
| "query", | |
| "contentAccess", | |
| "candidates", | |
| "decision", | |
| "steps", | |
| "citedNodeIds", | |
| "groundedOnly", | |
| "brainBinding", | |
| "controllerBoundary", | |
| "abstainReason" | |
| ], | |
| "additionalProperties": false | |
| } | |