---
title: opt-125m-fp8-dynamic
canonical_url: "https://www.modelscope.cn/models/nm-testing/opt-125m-fp8-dynamic"
md_url: "https://www.modelscope.cn/models/nm-testing/opt-125m-fp8-dynamic.md"
repository: nm-testing/opt-125m-fp8-dynamic
last_updated: 2025-08-10
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - opt
architectures:
  - OPTForCausalLM
parameters: 125.2M
tensor_type:
  - F16
  - F8_E4M3
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 823
stars: 0
tags:
  - fp8
---

# opt-125m-fp8-dynamic

> opt-125m-fp8-dynamic - nm-testing 在 ModelScope 开源的模型。Made with https://github.com/neuralmagic/AutoFP8:

nm-testing/opt-125m-fp8-dynamic 是 ModelScope 魔搭社区上的 125.2M 参数text-generation模型，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: nm-testing/opt-125m-fp8-dynamic
- **Tasks**: text-generation
- **Parameters**: 125.2M
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: fp8
- **Downloads**: 823
- **Stars**: 0
- **Last updated**: 2025-08-10

Source: https://www.modelscope.cn/models/nm-testing/opt-125m-fp8-dynamic

---

Made with https://github.com/neuralmagic/AutoFP8:
```
python quantize.py --model-id facebook/opt-125m --save-dir opt-125m-fp8-dynamic --activation-scheme dynamic
```