Instructions to use sollaholla/robocor-local-agent 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 sollaholla/robocor-local-agent 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 sollaholla/robocor-local-agent:Q8_0 # Run inference directly in the terminal: llama cli -hf sollaholla/robocor-local-agent:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf sollaholla/robocor-local-agent:Q8_0 # Run inference directly in the terminal: llama cli -hf sollaholla/robocor-local-agent:Q8_0
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 sollaholla/robocor-local-agent:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf sollaholla/robocor-local-agent:Q8_0
Use Docker
docker model run hf.co/sollaholla/robocor-local-agent:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use sollaholla/robocor-local-agent with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sollaholla/robocor-local-agent" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sollaholla/robocor-local-agent", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/sollaholla/robocor-local-agent:Q8_0
- Ollama
How to use sollaholla/robocor-local-agent with Ollama:
ollama run hf.co/sollaholla/robocor-local-agent:Q8_0
- Unsloth Desktop
- Pi
How to use sollaholla/robocor-local-agent with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sollaholla/robocor-local-agent:Q8_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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "sollaholla/robocor-local-agent:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use sollaholla/robocor-local-agent with Docker Model Runner:
docker model run hf.co/sollaholla/robocor-local-agent:Q8_0
- Lemonade
How to use sollaholla/robocor-local-agent with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sollaholla/robocor-local-agent:Q8_0
Run and chat with the model
lemonade run user.robocor-local-agent-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use sollaholla/robocor-local-agent with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sollaholla/robocor-local-agent:Q8_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://127.0.0.1:9931/v1 hermes config set model.default sollaholla/robocor-local-agent:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use sollaholla/robocor-local-agent with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sollaholla/robocor-local-agent:Q8_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://127.0.0.1:9931/v1 \ --custom-model-id "sollaholla/robocor-local-agent:Q8_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"
Robocor local agent v1: fine-tuned LFM2.5-VL-450M Q4_0, vision projector, llama-server for Jetson and Windows
fc9c234 verified |
Download README.md from sollaholla/robocor-local-agent: direct link, hf CLI and curl.
- Browser
- Download file 3.71 kB
-
https://huggingface.co/sollaholla/robocor-local-agent/resolve/main/README.md
- Command line
-
hf download hf://sollaholla/robocor-local-agent/README.md
-
curl -L -o README.md https://huggingface.co/sollaholla/robocor-local-agent/resolve/main/README.md
3.71 kB
| license: other | |
| license_name: lfm1.0 | |
| license_link: LICENSE | |
| base_model: LiquidAI/LFM2.5-VL-450M | |
| pipeline_tag: image-text-to-text | |
| tags: | |
| - robotics | |
| - tool-calling | |
| - gguf | |
| - llama.cpp | |
| - offline | |
| language: | |
| - en | |
| # Robocor local agent (450M, v1) | |
| The offline Agent model that runs on Robocor robots. It is | |
| [LiquidAI/LFM2.5-VL-450M](https://huggingface.co/LiquidAI/LFM2.5-VL-450M) | |
| fine-tuned to turn short operator commands into robot tool calls, and it | |
| describes pictures from the robot's camera with the stock vision projector. | |
| The Robocor app downloads these files itself the first time the robot needs | |
| them. Nothing here has to be installed by hand. | |
| ## Files | |
| | File | What it is | Size | | |
| | --- | --- | --- | | |
| | `robocor-agent-450m-v1-Q4_0.gguf` | Fine-tuned language model, Q4_0 | 219 MB | | |
| | `mmproj-robocor-agent-450m-v1-Q8_0.gguf` | Vision projector, Q8_0 (unchanged from the base model) | 103 MB | | |
| | `llama-server-v1-linux-arm64-cuda.tar.gz` | llama-server for NVIDIA Jetson (JetPack 6, CUDA 12.6) | 86 MB | | |
| | `llama-server-v1-windows-x64.zip` | llama-server for Windows x64, CPU | 17 MB | | |
| Both llama-server builds are llama.cpp at commit `f5222f2` with a small patch | |
| that limits tool arguments to the listed choices, so the model can only name | |
| places and outputs the robot really has. | |
| SHA-256: | |
| ``` | |
| dad3bb39ba0f60e4b4aea4a8b3b87d2350748f65784d9b7424609983a4f95f62 robocor-agent-450m-v1-Q4_0.gguf | |
| ebfc428baa37efad8bae93864f914b2634a09009f91ad59f974fe1a1565d8561 mmproj-robocor-agent-450m-v1-Q8_0.gguf | |
| 3e1b6e6054e6591544113ed5f2eeb73d2b6acc8d5fe5c31077f6f07ad23b327a llama-server-v1-linux-arm64-cuda.tar.gz | |
| 1b0c85aa433cfb4bb038b2ec190838b9b33aa86fb58526285d6ffe9abce13190 llama-server-v1-windows-x64.zip | |
| ``` | |
| ## What it does | |
| The model sees a fixed system prompt with the robot's state ("idle, battery | |
| 64%.") and up to eleven compact tools: `go_to`, `visit`, `shuttle`, `stop`, | |
| `dock`, `start_patrol`, `where_am_i`, `robot_status`, `take_snapshot`, | |
| `set_output` and `toggle_output`. Place and output arguments are closed lists | |
| filled from the robot's saved places and outputs. The app translates each call | |
| into the same tool the cloud Agent would use, so operator approvals and the | |
| chat transcript work the same way. | |
| It is meant for short commands: trips, stops, docking, patrols, outputs, | |
| "where are you", a status check and describing a camera picture. Settings, | |
| reports and longer tasks stay with the cloud Agent. | |
| ## Scores | |
| Exact-match accuracy on Robocor's held-out command sets, with the trained | |
| sampling (temperature 0.1, top_k 50, repeat penalty 1.1). Measured on an Apple | |
| M-series Mac with stock llama.cpp (no choice-list patch, which adds roughly | |
| half a point to two points). | |
| | Set | Cases | Accuracy | | |
| | --- | --- | --- | | |
| | Main commands | 400 | 98.5% | | |
| | Unexpected phrasings | 77 | 93.5% | | |
| | New unexpected phrasings | 251 | 80.9% | | |
| | Fresh set, written after training | 300 | 81.7% | | |
| On a Jetson Orin Nano the Q4_0 language model answers a command in about | |
| 0.35 seconds. | |
| ## Running it yourself | |
| ``` | |
| llama-server -m robocor-agent-450m-v1-Q4_0.gguf \ | |
| --mmproj mmproj-robocor-agent-450m-v1-Q8_0.gguf \ | |
| -ngl 99 -c 4096 -ub 256 -np 1 --cache-ram 0 --jinja --reasoning off | |
| ``` | |
| The chat template inside the GGUF is the LFM2.5 text template, because | |
| llama.cpp cannot build a tool grammar from the original VL template. | |
| ## License | |
| The model is a derivative of LFM2.5-VL-450M and is distributed under the | |
| [LFM Open License v1.0](LICENSE). The weights were changed by fine-tuning and | |
| the chat template was replaced, as described above. llama.cpp is MIT licensed; | |
| the Windows build includes the LLVM OpenMP runtime under its own license | |
| (`LICENSE-LLVM-OpenMP` in the zip). | |