Text Classification
GGUF
jev-style
English
jev
openjev
decision-model
typed-decisions
bonsai
ternary
local-inference
blackwell
conversational
Instructions to use ajh-code/Jev-Bonsai-Compass with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- jev-style
How to use ajh-code/Jev-Bonsai-Compass with jev-style:
pip install jev-style # GGUF builds score through llama.cpp: build the jev-score binary once hf download ajh-code/Jev-Bonsai-Compass build_jev_score.sh jev_score.cpp --local-dir jev-score export JEV_SCORE_BIN=$(sh jev-score/build_jev_score.sh /path/to/llama.cpp | tail -n 1)
from jev_style import JevStyle, noul, choice js = JevStyle.from_pretrained("ajh-code/Jev-Bonsai-Compass") out = js.decide("I was charged twice for one order.", { "billing": noul("This message is about billing."), "team": choice("Which team should handle it?", ["billing", "shipping", "tech"]), }) print(out["answers"]["team"]["choice"]) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ajh-code/Jev-Bonsai-Compass 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 ajh-code/Jev-Bonsai-Compass:Q2_0 # Run inference directly in the terminal: llama cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0 # Run inference directly in the terminal: llama cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0
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 ajh-code/Jev-Bonsai-Compass:Q2_0 # Run inference directly in the terminal: ./llama-cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0
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 ajh-code/Jev-Bonsai-Compass:Q2_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ajh-code/Jev-Bonsai-Compass:Q2_0
Use Docker
docker model run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
- LM Studio
- Jan
- Ollama
How to use ajh-code/Jev-Bonsai-Compass with Ollama:
ollama run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
- Unsloth Desktop
- Pi
How to use ajh-code/Jev-Bonsai-Compass with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
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": "ajh-code/Jev-Bonsai-Compass:Q2_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ajh-code/Jev-Bonsai-Compass with Docker Model Runner:
docker model run hf.co/ajh-code/Jev-Bonsai-Compass:Q2_0
- Lemonade
How to use ajh-code/Jev-Bonsai-Compass with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ajh-code/Jev-Bonsai-Compass:Q2_0
Run and chat with the model
lemonade run user.Jev-Bonsai-Compass-Q2_0
List all available models
lemonade list
- Hermes Agent
How to use ajh-code/Jev-Bonsai-Compass with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
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 ajh-code/Jev-Bonsai-Compass:Q2_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ajh-code/Jev-Bonsai-Compass with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ajh-code/Jev-Bonsai-Compass:Q2_0
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 "ajh-code/Jev-Bonsai-Compass:Q2_0" \ --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"
Download prepare_public.py from ajh-code/Jev-Bonsai-Compass: direct link, hf CLI and curl.
- Browser
- Download file 2.97 kB
-
https://huggingface.co/ajh-code/Jev-Bonsai-Compass/resolve/main/prepare_public.py
- Command line
-
hf download hf://ajh-code/Jev-Bonsai-Compass/prepare_public.py
-
curl -L -o prepare_public.py https://huggingface.co/ajh-code/Jev-Bonsai-Compass/resolve/main/prepare_public.py
2.97 kB
| #!/usr/bin/env python3 | |
| """Reconstruct decisions from privately held dataset snapshots and a case manifest.""" | |
| import argparse,csv,json | |
| from pathlib import Path | |
| def main(): | |
| p=argparse.ArgumentParser();p.add_argument('--snapshots',type=Path,required=True);p.add_argument('--manifest',type=Path,required=True) | |
| p.add_argument('--sources',type=Path,required=True);p.add_argument('--output',type=Path,required=True);a=p.parse_args() | |
| manifest=json.loads(a.manifest.read_text());sources={r['domain']:r for r in json.loads(a.sources.read_text())};cache={} | |
| with a.output.open('x') as out: | |
| for item in manifest['case_identifiers']['public']: | |
| domain=item['domain'];index=int(item['id'].rsplit('-',1)[1]) | |
| if domain=='banking20': | |
| if domain not in cache: | |
| with (a.snapshots/'banking-test.csv').open() as f:cache[domain]=list(csv.DictReader(f)) | |
| r=cache[domain][index];labels=sources[domain]['classes'] | |
| state=r['text'];question='Which banking support intent best matches the customer message?' | |
| options=[[x,x.replace('_',' ')] for x in labels];gold=r['category'] | |
| else: | |
| if domain not in cache: | |
| data=json.loads((a.snapshots/(domain+'-rows.json')).read_text()) | |
| cache[domain]=({x['row_idx']:x['row'] for x in data['rows']},next((f['type']['names'] for f in data['features'] if f['name']=='label'),None)) | |
| rows,names=cache[domain];r=rows[index] | |
| if domain in ['news','emotion']: | |
| state=r['text'];question='Which topic best describes this news item?' if domain=='news' else 'Which emotion is predominantly expressed by the author?' | |
| options=[[n,n] for n in names];gold=names[r['label']] | |
| elif domain=='reading': | |
| state=r['passage'];question='Based on the passage, answer yes or no: '+r['question'];options=[['yes','Yes'],['no','No']];gold='yes' if r['answer'] else 'no' | |
| elif domain=='entailment': | |
| state='Premise: '+r['premise']+'\nHypothesis: '+r['hypothesis'];question='Given only the premise, is the hypothesis entailed, contradicted, or neither (neutral)?' | |
| options=[['entailment','The premise entails the hypothesis'],['neutral','Neither entailed nor contradicted by the premise'],['contradiction','The premise contradicts the hypothesis']];gold=names[r['label']] | |
| elif domain=='science': | |
| state='Choose the best answer to this science question.';question=r['question'];options=list(map(list,zip(r['choices']['label'],r['choices']['text'])));gold=r['answerKey'] | |
| else:raise ValueError('Unknown domain '+domain) | |
| out.write(json.dumps(dict(id=item['id'],request=dict(state=state,question=question,options=options),expected=gold))+'\n') | |
| if __name__=='__main__':main() | |