---
title: Yi-1.5-6B-Chat-AWQ
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Yi-1.5-6B-Chat-AWQ"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Yi-1.5-6B-Chat-AWQ.md"
repository: AI-ModelScope/Yi-1.5-6B-Chat-AWQ
last_updated: 2024-05-13
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 1.3B
tensor_type:
  - I32
  - F16
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: 81
stars: 0
---

# Yi-1.5-6B-Chat-AWQ

> Yi-1.5-6B-Chat-AWQ - AI-ModelScope 在 ModelScope 开源的模型。language: en zh pipelinetag: text-generation tags: Awq int4 yi1.5-6B-Chat pytorch license: Apache 2.0 licensename: Apache 2.0 licenselink: LICENSE ---

AI-ModelScope/Yi-1.5-6B-Chat-AWQ 是 ModelScope 魔搭社区上的 1.3B 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/Yi-1.5-6B-Chat-AWQ
- **Tasks**: text-generation
- **Parameters**: 1.3B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 81
- **Stars**: 0
- **Last updated**: 2024-05-13

Source: https://www.modelscope.cn/models/AI-ModelScope/Yi-1.5-6B-Chat-AWQ

---

language:
- en
- zh
pipeline_tag: text-generation
tags:
- Awq
- int4
- yi1.5-6B-Chat
- pytorch
license: Apache 2.0
license_name: Apache 2.0
license_link: LICENSE
---

## About Quantization
我们使用modelscope [swift](https://github.com/modelscope/swift/)仓库进行AWQ 4bit量化. 量化文档可以查看[这里](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md). 量化命令如下:

We use the modelscope [swift](https://github.com/modelscope/swift/) repository to perform AWQ 4bit quantization. Quantization documentation can be found [here](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/LLM-quantization.md). The quantization command is as follows:

```bash
# Experimental Environment: A100
swift export \
    --quant_bits 4 \
    --model_type yi-1_5-6b-chat \
    --quant_method awq \
    --quant_n_samples 64 \
    --dataset alpaca-zh alpaca-en sharegpt-gpt4-mini \
    --quant_seqlen 4096
```

Inference:
```bash
CUDA_VISIBLE_DEVICES=0 swift infer --model_type yi-1_5-6b-chat-awq-int4
```

SFT:
```bash
CUDA_VISIBLE_DEVICES=0 swift sft --model_type yi-1_5-6b-chat-awq-int4 --dataset leetcode-python-en
```

Original Model:

[YI1.5-6B-Chat](https://modelscope.cn/models/01ai/Yi-1.5-6B-Chat/summary)