---
title: Yi_34B_Chat_2bit
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/Yi_34B_Chat_2bit"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/Yi_34B_Chat_2bit.md"
repository: AI-ModelScope/Yi_34B_Chat_2bit
last_updated: 2023-12-06
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
parameters: 5.1B
tensor_type:
  - F16
  - I64
  - I16
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: 122
stars: 4
tags:
  - 2bit
  - llama
  - yi
  - 34b
---

# Yi_34B_Chat_2bit

> Yi_34B_Chat_2bit - AI-ModelScope 在 ModelScope 开源的模型。You can run it on 11G mem GPU,quantize base QuIP# method, a weights-only quantization method that is able to achieve near fp16 performance using only 2 bits per weight.

AI-ModelScope/Yi_34B_Chat_2bit 是 ModelScope 魔搭社区上的 5.1B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/Yi_34B_Chat_2bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 5.1B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: 2bit, llama, yi, 34b
- **Downloads**: 122
- **Stars**: 4
- **Last updated**: 2023-12-06

Source: https://www.modelscope.cn/models/AI-ModelScope/Yi_34B_Chat_2bit

---

You can run it on 11G mem GPU,quantize base QuIP# method, a weights-only quantization method that is able to achieve near fp16 performance using only 2 bits per weight.

url:https://github.com/Cornell-RelaxML/quip-sharp