README.md

metadata

license: apache-2.0
library_name: transformers
pipeline_tag: text-generation

Starling-LM-10.7B-beta

This is Starling-LM-10.7B-beta, a depth-upscaled version of Nexusflow/Starling-LM-7B-beta.

This model is intended to be used as a drop-in upgrade from the original 7 billion parameter model.

GGUF quantizations (courtesy of bartowski)

See bartowski/Starling-LM-10.7B-beta-GGUF

ExLlamaV2 quantizations (courtesy of blockblockblock)

• 2.5 bpw
• 3 bpw
• 3.5 bpw
• 3.7 bpw
• 4 bpw
• 4.4 bpw
• 4.6 bpw
• 4.8 bpw
• 5 bpw
• 5.5 bpw
• 6 bpw