Text Generation
Safetensors
GGUF
English
qwen2_5_vl
nuextract
extraction
json
schedule
rrule
ical
rfc5545
structured-data
conversational
Instructions to use connect211/RRULE_Extractor 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 connect211/RRULE_Extractor 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 connect211/RRULE_Extractor:Q4_K_M # Run inference directly in the terminal: llama cli -hf connect211/RRULE_Extractor:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf connect211/RRULE_Extractor:Q4_K_M # Run inference directly in the terminal: llama cli -hf connect211/RRULE_Extractor:Q4_K_M
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 connect211/RRULE_Extractor:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf connect211/RRULE_Extractor:Q4_K_M
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 connect211/RRULE_Extractor:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf connect211/RRULE_Extractor:Q4_K_M
Use Docker
docker model run hf.co/connect211/RRULE_Extractor:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use connect211/RRULE_Extractor with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "connect211/RRULE_Extractor" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "connect211/RRULE_Extractor", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/connect211/RRULE_Extractor:Q4_K_M
- Ollama
How to use connect211/RRULE_Extractor with Ollama:
ollama run hf.co/connect211/RRULE_Extractor:Q4_K_M
- Unsloth Studio
How to use connect211/RRULE_Extractor 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 connect211/RRULE_Extractor 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 connect211/RRULE_Extractor to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for connect211/RRULE_Extractor to start chatting
- Docker Model Runner
How to use connect211/RRULE_Extractor with Docker Model Runner:
docker model run hf.co/connect211/RRULE_Extractor:Q4_K_M
- Lemonade
How to use connect211/RRULE_Extractor with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull connect211/RRULE_Extractor:Q4_K_M
Run and chat with the model
lemonade run user.RRULE_Extractor-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| {%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%} | |
| {%- for message in messages -%} | |
| {%- if message['role'] == 'system' -%} | |
| {{- '<|im_start|>system | |
| ' -}} | |
| {%- if message['content'] is string -%} | |
| {{- message['content'] | trim -}} | |
| {%- endif -%} | |
| {{- '<|im_end|> | |
| ' -}} | |
| {%- elif message['role'] == 'user' -%} | |
| {%- if loop.first -%} | |
| {{- '<|im_start|>system | |
| ' -}} | |
| {%- if template -%} | |
| {#--- If template, extraction task ---#} | |
| {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}} | |
| {%- else -%} | |
| {#--- Else, template generation task ---#} | |
| {{- 'You are a helpful assistant.' -}} | |
| {%- endif -%} | |
| {{ '<|im_end|> | |
| ' }} | |
| {%- endif -%} | |
| {{- '<|im_start|>' + message['role'] + ' | |
| ' -}} | |
| {%- if template -%} | |
| {#--- Template Section ---#} | |
| {{- '# Template: | |
| ' -}} | |
| {{- template -}} | |
| {{- ' | |
| ' -}} | |
| {%- if examples -%} | |
| {#--- Examples can only exist in the extraction task ---#} | |
| {{- '# Examples: | |
| ' -}} | |
| {%- for example in examples -%} | |
| {{- '## Input: | |
| ' -}} | |
| {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%} | |
| {{- image_placeholder | trim -}} | |
| {%- elif example['input'] == '<image>' -%} | |
| {#--- Keep compatibility with <image> for now ---#} | |
| {{- image_placeholder | trim -}} | |
| {%- else -%} | |
| {#--- Text input example ---#} | |
| {{- example['input'] -}} | |
| {%- endif -%} | |
| {{- ' | |
| ' -}} | |
| {{- '## Output: | |
| ' -}} | |
| {{- example['output'] -}} | |
| {{- ' | |
| ' -}} | |
| {%- endfor -%} | |
| {%- endif -%} | |
| {{- '# Context: | |
| ' -}} | |
| {%- endif -%} | |
| {%- if message['content'] is string -%} | |
| {#--- Simple string content ---#} | |
| {{- message['content'] | trim -}} | |
| {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%} | |
| {{- image_placeholder | trim -}} | |
| {%- else -%} | |
| {#--- List of content items (mixed text/images) ---#} | |
| {#--- First, determine what the actual input content is (not ICL images) ---#} | |
| {%- set ns = namespace(has_text_input=false, text_content='') -%} | |
| {#--- Count content types and identify actual input document ---#} | |
| {%- for content in message['content'] -%} | |
| {%- if content is mapping and content.get('type') == 'text' -%} | |
| {%- if content.get('text') != '<image>' -%} | |
| {#--- Keep compatibility with <image> for now ---#} | |
| {%- set ns.has_text_input = true -%} | |
| {%- set ns.text_content = content['text'] -%} | |
| {%- endif -%} | |
| {%- elif content is string -%} | |
| {%- if content != '<image>' -%} | |
| {#--- Keep compatibility with <image> for now ---#} | |
| {%- set ns.has_text_input = true -%} | |
| {%- set ns.text_content = content -%} | |
| {%- endif -%} | |
| {%- endif -%} | |
| {%- endfor -%} | |
| {#--- Determine what to output based on actual input type ---#} | |
| {%- if ns.has_text_input -%} | |
| {#--- Main input is text, so output the text content ---#} | |
| {{- ns.text_content | trim -}} | |
| {%- else -%} | |
| {#--- Main input is image or <image> placeholder ---#} | |
| {%- set ns2 = namespace(found_image=false) -%} | |
| {%- for content in message['content'] -%} | |
| {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%} | |
| {{- image_placeholder | trim -}} | |
| {%- set ns2.found_image = true -%} | |
| {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%} | |
| {#--- Keep compatibility with <image> for now ---#} | |
| {{- image_placeholder | trim -}} | |
| {%- set ns2.found_image = true -%} | |
| {%- elif content is string and content == '<image>' and not ns2.found_image -%} | |
| {#--- Keep compatibility with <image> for now ---#} | |
| {{- image_placeholder | trim -}} | |
| {%- set ns2.found_image = true -%} | |
| {%- endif -%} | |
| {%- endfor -%} | |
| {%- endif -%} | |
| {%- endif -%} | |
| {{- '<|im_end|> | |
| '}} | |
| {%- elif message['role'] == 'assistant' -%} | |
| {{- '<|im_start|>assistant | |
| ' -}} | |
| {%- if message['content'] is string -%} | |
| {{- message['content'] | trim -}} | |
| {%- elif message['content'] is iterable and message['content'] is not string -%} | |
| {%- for content in message['content'] -%} | |
| {%- if content is mapping and content.get('type') == 'text' -%} | |
| {{- content['text'] | trim -}} | |
| {%- elif content is string -%} | |
| {{- content | trim -}} | |
| {%- endif -%} | |
| {%- endfor -%} | |
| {%- endif -%} | |
| {{- '<|im_end|> | |
| ' -}} | |
| {%- endif -%} | |
| {%- endfor -%} | |
| {%- if add_generation_prompt -%} | |
| {{- '<|im_start|>assistant | |
| ' -}} | |
| {%- endif -%} |