DeepSeek-Coder-V2-Lite-Instruct — 1BP format

deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct (mit) converted to 1BP format.

Property	Value
Parameters	16B
Architecture	deepseek2
Quantization	Q4NX (4-bit)
Source	deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Format	.1bp

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bong-water-water-bong/DeepSeek-Coder-V2-Lite-Instruct-1BP

Base model

Finetuned

(18)

this model