Readme

Falcon3 represents TII’s latest advancement in efficient language models under 10B parameters, focused on enhancing science, math, and code capabilities while maintaining training efficiency.

Key Features

• Sizes: 10B
• Depth up-scaling technique used to create 10B model from 7B
• Knowledge distillation for smaller models (1B, 3B)

Performance Highlights

• falcon3:10b achieves SOTA in under-13B category

• Extended context length up to 32K tokens

  Tool usage in action

  

Test code:

import ollama

client = ollama.Client(host='http://localhost:11434')
response = client.chat(
    model='falcon3-tools',
    messages=[{'role': 'user', 'content':
        'Get me a tool to use for hack'}],

		# provide a tool selector function
    tools=[{
      'type': 'function',
      'function': {
        'name': 'get_me_a_tool',
        'description': 'Get a tool to use',
        'parameters': {
          'type': 'object',
          'properties': {
            'tool': {
              'type': 'string',
              'description': 'The name of the tool',
            },
          },
          'required': ['tool'],
        },
      },
    },
  ],
)

print(response['message']['tool_calls'])

Expected results:

References:

https://huggingface.co/blog/falcon3