Text Generation
LiteRT-LM
English
custom
hermes-edge
mobile-ai
on-device
ios
iphone-16
apple-neural-engine
deepseek
dspark
speculative-decoding
hermes-agent
tool-calling
raven-ecosystem
Instructions to use bclermo/hermes-edge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use bclermo/hermes-edge with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=bclermo/hermes-edge \ model.litertlm \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
| {"messages": [{"role": "user", "content": "What is 12 * 9?"}, {"role": "assistant", "content": "<tool_call>{\"name\": \"calculator\", \"arguments\": {\"expression\": \"12*9\"}}</tool_call>"}, {"role": "tool", "content": "108"}, {"role": "assistant", "content": "12 * 9 = 108."}], "tools": [{"name": "calculator", "description": "Evaluate an arithmetic expression.", "parameters": {"type": "object", "properties": {"expression": {"type": "string"}}, "required": ["expression"]}}]} | |
| {"messages": [{"role": "user", "content": "Who won the 2022 FIFA World Cup?"}, {"role": "assistant", "content": "<tool_call>{\"name\": \"web_search\", \"arguments\": {\"query\": \"2022 FIFA World Cup winner\"}}</tool_call>"}, {"role": "tool", "content": "Argentina won the 2022 FIFA World Cup, defeating France on penalties."}, {"role": "assistant", "content": "Argentina won the 2022 FIFA World Cup, beating France in the final on penalties."}], "tools": [{"name": "web_search", "description": "Search the web.", "parameters": {"type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]}}]} | |
| {"messages": [{"role": "user", "content": "Hello! What can you do?"}, {"role": "assistant", "content": "Hi! I'm Hermes, an on-device assistant. I can chat, do math with my calculator tool, and look things up on the web. How can I help?"}]} | |