neuralmagic
/

Qwen2-1.5B-Instruct-quantized.w8a8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Qwen2-1.5B-Instruct-quantized.w8a8 / config.json

Commit History

Updated compression_config to quantization_config

28f339d
verified

mgoin commited on Oct 9, 2024

Upload folder using huggingface_hub

31d9b0f
verified

alexmarques commited on Jul 11, 2024