---
title: Llama-2-70b-AQLM-2Bit-2x8-hf
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Llama-2-70b-AQLM-2Bit-2x8-hf"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Llama-2-70b-AQLM-2Bit-2x8-hf.md"
repository: AI-ModelScope/Llama-2-70b-AQLM-2Bit-2x8-hf
last_updated: 2024-03-11
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 17.6B
tensor_type:
  - F16
  - I8
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 5016
stars: 0
---

# Llama-2-70b-AQLM-2Bit-2x8-hf

> Llama-2-70b-AQLM-2Bit-2x8-hf - AI-ModelScope 在 ModelScope 开源的模型。Official AQLM quantization of meta-llama/Llama-2-7b-hf.

AI-ModelScope/Llama-2-70b-AQLM-2Bit-2x8-hf 是 ModelScope 魔搭社区上的 17.6B 参数text-generation模型，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/Llama-2-70b-AQLM-2Bit-2x8-hf
- **Tasks**: text-generation
- **Parameters**: 17.6B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 5016
- **Stars**: 0
- **Last updated**: 2024-03-11

Source: https://www.modelscope.cn/models/AI-ModelScope/Llama-2-70b-AQLM-2Bit-2x8-hf

---

Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of `meta-llama/Llama-2-7b-hf`.

For this quantization, we used 1 codebook of 16 bits.

Selected evaluation results for this and other models: 

| Model      | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link                                                                 |
|------------|-------------|----------------|----------------|--------------------------------------------------------------------------|
| Llama-2-7b | 1x16        | 5.92          | 2.4            | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf) |
| Llama-2-7b | 2x8         | 6.69          | 2.2            | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf)  |
| Llama-2-7b | 8x8         | 6.61          | 2.2            | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-8x8-hf)  |
| Llama-2-13b| 1x16        | 5.22           | 4.1            | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf)|
| Llama-2-70b| 1x16        | 3.83           | 18.8           | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-70b-AQLM-2Bit-1x16-hf)|
| Llama-2-70b (THIS) | 2x8         | 4.21           | 18.2           | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-70b-AQLM-2Bit-2x8-hf) |
| Mixtral-8x7b| 1x16       | 3.35           | 12.6            | [Link](https://huggingface.co/ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf)|
| Mixtral-8x7b-Instruct| 1x16       | -           | 12.6            | [Link](https://huggingface.co/ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf)|

To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM).