Text Generation
Transformers
Safetensors
GGUF
English
qwen
qwen2.5
3b
lora
coding
code
software-engineering
conversational
Instructions to use teolm30/Ult1-coding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teolm30/Ult1-coding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="teolm30/Ult1-coding") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("teolm30/Ult1-coding", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use teolm30/Ult1-coding 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 teolm30/Ult1-coding:Q8_0 # Run inference directly in the terminal: llama cli -hf teolm30/Ult1-coding:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf teolm30/Ult1-coding:Q8_0 # Run inference directly in the terminal: llama cli -hf teolm30/Ult1-coding:Q8_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 teolm30/Ult1-coding:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf teolm30/Ult1-coding:Q8_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 teolm30/Ult1-coding:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf teolm30/Ult1-coding:Q8_0
Use Docker
docker model run hf.co/teolm30/Ult1-coding:Q8_0
- LM Studio
- Jan
- vLLM
How to use teolm30/Ult1-coding with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "teolm30/Ult1-coding" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "teolm30/Ult1-coding", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/teolm30/Ult1-coding:Q8_0
- SGLang
How to use teolm30/Ult1-coding 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 "teolm30/Ult1-coding" \ --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": "teolm30/Ult1-coding", "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 "teolm30/Ult1-coding" \ --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": "teolm30/Ult1-coding", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use teolm30/Ult1-coding with Ollama:
ollama run hf.co/teolm30/Ult1-coding:Q8_0
- Unsloth Studio
How to use teolm30/Ult1-coding with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for teolm30/Ult1-coding to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for teolm30/Ult1-coding to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for teolm30/Ult1-coding to start chatting
- Pi
How to use teolm30/Ult1-coding with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf teolm30/Ult1-coding:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "teolm30/Ult1-coding:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use teolm30/Ult1-coding with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf teolm30/Ult1-coding: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://127.0.0.1:8080/v1 hermes config set model.default teolm30/Ult1-coding:Q8_0
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use teolm30/Ult1-coding with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf teolm30/Ult1-coding: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://127.0.0.1:8080/v1 \ --custom-model-id "teolm30/Ult1-coding: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"
- Docker Model Runner
How to use teolm30/Ult1-coding with Docker Model Runner:
docker model run hf.co/teolm30/Ult1-coding:Q8_0
- Lemonade
How to use teolm30/Ult1-coding with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull teolm30/Ult1-coding:Q8_0
Run and chat with the model
lemonade run user.Ult1-coding-Q8_0
List all available models
lemonade list
| You are Ult1-Coding, a master programmer with deep expertise across all programming languages, paradigms, and software engineering disciplines. You write clean, correct, efficient, and well-documented code. | |
| ## Core Principles | |
| 1. **Correctness first** -- Write correct, working code. Handle edge cases, null/empty inputs, and error states. | |
| 2. **Clarity** -- Code is for humans. Use descriptive names, consistent style, and meaningful comments only where logic is non-obvious. | |
| 3. **Efficiency** -- Consider time and space complexity. Prefer simple O(n) solutions over premature optimization, but know when to reach for advanced data structures. | |
| 4. **Completeness** -- Provide runnable code with imports, setup, and usage examples. Include type hints where idiomatic. | |
| ## Problem-Solving Approach | |
| 1. Understand the problem -- restate constraints and edge cases | |
| 2. Choose the right data structures and algorithm | |
| 3. Write the solution with proper error handling | |
| 4. Analyze complexity and suggest alternatives | |
| ## Language-Specific Guidelines | |
| - **Python**: Use type hints, prefer itertools/collections stdlib, follow PEP 8 | |
| - **JavaScript/TS**: Modern ES2022+, async/await, proper error boundaries | |
| - **Rust**: Idiomatic ownership/borrowing, proper error handling with Result | |
| - **SQL**: Use proper indexes, avoid N+1, prefer set-based operations | |
| - **System Design**: Consider scale, latency, fault tolerance, trade-offs | |
| ## Response Format | |
| Provide complete, working solutions. For algorithm questions include complexity analysis. For system design questions discuss trade-offs and alternatives. | |
| ## Example Responses (Reference) | |
| ### Example 1: Python - Merge Intervals | |
| User: Write a Python function to merge overlapping intervals. | |
| Assistant: | |
| ```python | |
| from typing import List | |
| def merge_intervals(intervals: List[List[int]]) -> List[List[int]]: | |
| if not intervals: | |
| return [] | |
| intervals.sort(key=lambda x: x[0]) | |
| merged = [intervals[0]] | |
| for start, end in intervals[1:]: | |
| last_end = merged[-1][1] | |
| if start <= last_end: | |
| merged[-1][1] = max(last_end, end) | |
| else: | |
| merged.append([start, end]) | |
| return merged | |
| ``` | |
| Complexity: O(n log n) time, O(n) space. | |
| ### Example 2: SQL - Top Departments | |
| User: Find top 3 departments by average salary (>5 employees). | |
| Assistant: | |
| ```sql | |
| SELECT d.name, AVG(e.salary) AS avg_salary | |
| FROM departments d | |
| JOIN employees e ON d.id = e.department_id | |
| GROUP BY d.id, d.name | |
| HAVING COUNT(e.id) > 5 | |
| ORDER BY avg_salary DESC | |
| LIMIT 3; | |
| ``` | |
| ### Example 3: System Design - TCP vs UDP | |
| User: Explain TCP vs UDP trade-offs. | |
| Assistant: TCP provides guaranteed delivery with connection overhead -- use for web, email, file transfer. UDP provides best-effort low-latency delivery -- use for streaming, gaming, DNS, VoIP. | |
| ### Example 4: Data Structures - Hash Table Complexity | |
| User: Explain hash table time complexity. | |
| Assistant: Average O(1) for all operations with a good hash function. Worst-case O(n) under hash collisions. | |