Zenabius
/

Qwen2.5-3B-Instruct-exl2

8-bit precision

Model card Files Files and versions Community

Qwen2.5-3B-Instruct-exl2 / README.md

Zenabius's picture

Update README.md

467484e verified 8 days ago

|

history blame contribute delete

225 Bytes

metadata

base_model:
  - Qwen/Qwen2.5-3B-Instruct

EXL2 Quantizations of Qwen2.5-3B-Instruct

Using exllamav2 release 0.2.6 for quantization.

Original model: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct

Bits 8.0, lm_head 8.0