Qwen2.5 7B Instruct

Permissive

Alibaba · Qwen · Released 2024-09

7BText

One of the strongest fully-permissive 7B models available, with unusually good math and coding for its size.

Strengths

  • +Apache 2.0, no usage restrictions
  • +Strong math/coding relative to size
  • +128K context window

Limitations

  • -General knowledge trails larger Qwen2.5 tiers
  • -Chinese-centric training data skews some outputs

License

Apache 2.0

use commercially with attribution niceties

Hardware

runs on a good consumer GPU (or Apple Silicon) with quantization

Links

Stats

Qwen/Qwen2.5-7B-Instruct— downloads·— likes

via Hugging Face

Related models