Text Generation
Safetensors
GGUF
English
qwen2
transit
gtfs
transportation
instruction-following
qlora
unsloth
conversational
Instructions to use umarfarookm/UmarTransit-1B 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 umarfarookm/UmarTransit-1B 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 umarfarookm/UmarTransit-1B:Q4_K_M # Run inference directly in the terminal: llama cli -hf umarfarookm/UmarTransit-1B:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf umarfarookm/UmarTransit-1B:Q4_K_M # Run inference directly in the terminal: llama cli -hf umarfarookm/UmarTransit-1B:Q4_K_M
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 umarfarookm/UmarTransit-1B:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf umarfarookm/UmarTransit-1B:Q4_K_M
Use Docker
docker model run hf.co/umarfarookm/UmarTransit-1B:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use umarfarookm/UmarTransit-1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "umarfarookm/UmarTransit-1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "umarfarookm/UmarTransit-1B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/umarfarookm/UmarTransit-1B:Q4_K_M
- Ollama
How to use umarfarookm/UmarTransit-1B with Ollama:
ollama run hf.co/umarfarookm/UmarTransit-1B:Q4_K_M
- Unsloth Desktop
- Pi
How to use umarfarookm/UmarTransit-1B with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf umarfarookm/UmarTransit-1B:Q4_K_M
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": "umarfarookm/UmarTransit-1B:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use umarfarookm/UmarTransit-1B with Docker Model Runner:
docker model run hf.co/umarfarookm/UmarTransit-1B:Q4_K_M
- Lemonade
How to use umarfarookm/UmarTransit-1B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull umarfarookm/UmarTransit-1B:Q4_K_M
Run and chat with the model
lemonade run user.UmarTransit-1B-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use umarfarookm/UmarTransit-1B with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf umarfarookm/UmarTransit-1B:Q4_K_M
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 umarfarookm/UmarTransit-1B:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use umarfarookm/UmarTransit-1B with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf umarfarookm/UmarTransit-1B:Q4_K_M
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 "umarfarookm/UmarTransit-1B:Q4_K_M" \ --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"
Update README.md
Browse files
README.md
CHANGED
|
@@ -54,6 +54,14 @@ Evaluated on 335 held-out test pairs across 8 task categories:
|
|
| 54 |
**Best performing:** Transfer analysis (ROUGE-L: 0.90)
|
| 55 |
**Needs improvement:** GTFS knowledge (ROUGE-L: 0.38) — limited training data (22 pairs)
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
## Training Data
|
| 58 |
|
| 59 |
The model was trained on synthetic instruction-response pairs generated from **15 real public GTFS feeds** across **10 countries**:
|
|
|
|
| 54 |
**Best performing:** Transfer analysis (ROUGE-L: 0.90)
|
| 55 |
**Needs improvement:** GTFS knowledge (ROUGE-L: 0.38) — limited training data (22 pairs)
|
| 56 |
|
| 57 |
+
## Available Formats
|
| 58 |
+
|
| 59 |
+
| Format | File | Size | Use Case |
|
| 60 |
+
|--------|------|------|----------|
|
| 61 |
+
| Safetensors | `model.safetensors` | 3.09 GB | Full precision — Transformers/Python |
|
| 62 |
+
| GGUF Q4_K_M | `UmarTransit-1B.Q4_K_M.gguf` | 986 MB | 4-bit — Ollama/llama.cpp (recommended) |
|
| 63 |
+
| GGUF Q8_0 | `UmarTransit-1B.Q8_0.gguf` | 1.65 GB | 8-bit — Ollama/llama.cpp (higher quality) |
|
| 64 |
+
|
| 65 |
## Training Data
|
| 66 |
|
| 67 |
The model was trained on synthetic instruction-response pairs generated from **15 real public GTFS feeds** across **10 countries**:
|