btrabucco/Insta-Qwen3-1.7B-SFT

The btrabucco/Insta-Qwen3-1.7B-SFT is a 1.7 billion parameter language model developed by btrabucco. This model is a fine-tuned variant, likely based on the Qwen3 architecture, and is designed for specific instruction-following tasks. With a substantial context length of 40960 tokens, it is optimized for processing and generating longer sequences of text. Its primary application is in scenarios requiring robust instruction adherence and extended contextual understanding.

Warm
Public
2B
BF16
32768
Hugging Face

No reviews yet. Be the first to review!