Qwen2-1.5B-Instruct-Function-Calling-v1

Generate text responses to prompts with function calling capabilities, enabling natural language conversations, content creation, and tool usage

Model Properties

The pipeline consists of a prefill step and a token-by-token step, fine-tuned for function calling tasks. This model is a fine-tuned version of Qwen/Qwen2-1.5B-Instruct on devanshamin/gem-viggo-function-calling dataset.

License Name: Apache License 2.0
Number Of Parameters: 1.5B
Model Size: 2.99 GB

Select device..

Hailo-10h

Technical Details

Operations: 29.4 GOPs per input token

Context Length: 2048

Numerical Scheme: A8W4, symmetric, channel-wise

Inference Api: C++, Python

Compiled Model:

Performance Metrics

Load Time In Sec 7.91

Time To First Token In Sec 0.4

Tps 6.23

0/5 (0 Reviews)