Text Generation
Transformers
Safetensors
English
qwen2
business-intelligence
market-analysis
web-research
agent
tool-calling
business-consultancy
autonomous-agent
competitive-intelligence
trend-forecasting
chatpbc
luwa
conversational
text-generation-inference
Instructions to use chatpbc11121/luwa-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chatpbc11121/luwa-01 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="chatpbc11121/luwa-01") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("chatpbc11121/luwa-01") model = AutoModelForCausalLM.from_pretrained("chatpbc11121/luwa-01", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use chatpbc11121/luwa-01 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "chatpbc11121/luwa-01" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chatpbc11121/luwa-01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/chatpbc11121/luwa-01
- SGLang
How to use chatpbc11121/luwa-01 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 "chatpbc11121/luwa-01" \ --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": "chatpbc11121/luwa-01", "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 "chatpbc11121/luwa-01" \ --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": "chatpbc11121/luwa-01", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use chatpbc11121/luwa-01 with Docker Model Runner:
docker model run hf.co/chatpbc11121/luwa-01
| { | |
| "agent_name": "luwa-01", | |
| "agent_version": "1.0.0", | |
| "developer": "ChatPBC", | |
| "description": "Autonomous business intelligence agent with web research and tool-calling capabilities", | |
| "reasoning_mode": "business_consultant", | |
| "max_tool_calls_per_query": 5, | |
| "confidence_threshold": 0.7, | |
| "output_format": "structured_markdown", | |
| "capabilities": { | |
| "web_search": true, | |
| "web_scraping": true, | |
| "market_analysis": true, | |
| "trend_forecasting": true, | |
| "business_consultancy": true, | |
| "competitive_intelligence": true, | |
| "business_ideation": true, | |
| "tool_calling": true, | |
| "multi_step_reasoning": true, | |
| "data_synthesis": true, | |
| "strategic_planning": true | |
| }, | |
| "tools": [ | |
| { | |
| "name": "web_search", | |
| "description": "Search the web for current, real-time information, news, and data", | |
| "parameters": { | |
| "query": {"type": "string", "required": true, "description": "Search query"}, | |
| "num_results": {"type": "integer", "default": 5, "description": "Number of results"} | |
| } | |
| }, | |
| { | |
| "name": "web_scrape", | |
| "description": "Extract full content from a specific webpage or report", | |
| "parameters": { | |
| "url": {"type": "string", "required": true, "description": "URL to scrape"}, | |
| "max_chars": {"type": "integer", "default": 3000, "description": "Max characters to extract"} | |
| } | |
| }, | |
| { | |
| "name": "market_data", | |
| "description": "Get market size, growth rate, TAM/SAM/SOM, and investment data for a sector", | |
| "parameters": { | |
| "sector": {"type": "string", "required": true, "description": "Industry sector"}, | |
| "metric": {"type": "string", "default": "", "description": "Specific metric (revenue, growth, TAM)"}, | |
| "region": {"type": "string", "default": "global", "description": "Geographic region"} | |
| } | |
| }, | |
| { | |
| "name": "news_analysis", | |
| "description": "Analyze recent news, developments, and regulatory changes", | |
| "parameters": { | |
| "topic": {"type": "string", "required": true, "description": "Topic to analyze"}, | |
| "timeframe": {"type": "string", "default": "30d", "description": "Time window (7d, 30d, 90d)"}, | |
| "focus": {"type": "string", "default": "", "description": "Angle (regulatory, funding, launches)"} | |
| } | |
| }, | |
| { | |
| "name": "competitor_analysis", | |
| "description": "Analyze competitors: positioning, pricing, features, market share", | |
| "parameters": { | |
| "market": {"type": "string", "required": true, "description": "Market/industry"}, | |
| "focus": {"type": "string", "default": "", "description": "Focus area (pricing, features, positioning)"}, | |
| "competitors": {"type": "array", "default": [], "description": "Specific competitors"} | |
| } | |
| }, | |
| { | |
| "name": "trend_forecast", | |
| "description": "Forecast industry trends, emerging patterns, and future projections", | |
| "parameters": { | |
| "industry": {"type": "string", "required": true, "description": "Industry to forecast"}, | |
| "horizon": {"type": "string", "default": "1 year", "description": "Forecast horizon"}, | |
| "factors": {"type": "array", "default": [], "description": "Factors to consider"} | |
| } | |
| } | |
| ], | |
| "agent_loop": { | |
| "steps": [ | |
| "parse_query", | |
| "determine_tools_needed", | |
| "execute_tools_sequentially", | |
| "analyze_results", | |
| "synthesize_report", | |
| "deliver_response" | |
| ], | |
| "description": "Autonomous reasoning loop that chains tool calls and synthesizes findings into actionable business intelligence" | |
| }, | |
| "model_architecture": "transformer", | |
| "hidden_size": 896, | |
| "num_hidden_layers": 24, | |
| "num_attention_heads": 14, | |
| "vocab_size": 152064, | |
| "max_position_embeddings": 32768, | |
| "inference_latency": "<100ms on GPU, <1s on CPU", | |
| "cost_per_query": "$0.00001" | |
| } | |