---
license: other
license_name: qianwen
license_link: https://huggingface.co/Qwen/Qwen-72B-Chat/blob/main/LICENSE
---

This is 2-bit quantization of [Qwen/Qwen-72B-Chat](https://huggingface.co/Qwen/Qwen-72B-Chat) using [QuIP#](https://cornell-relaxml.github.io/quip-sharp/)

Random samples from C4 and [SkyPile](https://huggingface.co/datasets/Skywork/SkyPile-150B) are used as calibration data.

## Model loading
Please follow the instruction of [QuIP-for-all](https://github.com/chu-tianxiang/QuIP-for-all) for usage.

As an alternative, you can use [vLLM branch](https://github.com/chu-tianxiang/vllm-gptq/tree/quip_gemv) for faster inference. QuIP has to launch like 5 kernels for each linear layer, so it's very helpful for vLLM to use cuda-graph to reduce launching overhead. BTW, If you have problem installing fast-hadamard-transform from pip, you can also install it from [source](https://github.com/Dao-AILab/fast-hadamard-transform)

## Perplexity
Measured at Wikitext with 4096 context length
| fp16 | 2-bit |
| ------- | ------- |
| 5.8438  | 7.3047  |

## Speed

Latency and throughput are measured using vLLM (`examples/benchmark_latency.py` and `examples/benchmark_throughput.py` respectively) at single A100-80G.

Latency at batch size 1: 13.5 tokens/s.

Throughput:  0.77 requests/s