---
title: ftp1_v0426_50kstep
canonical_url: "https://www.modelscope.cn/models/michaelyuancb/ftp1_v0426_50kstep"
md_url: "https://www.modelscope.cn/models/michaelyuancb/ftp1_v0426_50kstep.md"
repository: michaelyuancb/ftp1_v0426_50kstep
last_updated: 2026-06-04
license: MIT
parameters: 4.1B
tensor_type:
  - BF16
  - F32
library_name:
  - safetensors
downloads: 1982
stars: 0
---

# ftp1_v0426_50kstep

> ftp1_v0426_50kstep - michaelyuancb 在 ModelScope 开源的模型。ftp1pretrainv042650kstep is the 50k-step pretrained checkpoint of FTP-1, a general tactile policy for multimodal manipulation with vision, proprioception, language, and optional tactile input.

michaelyuancb/ftp1_v0426_50kstep 是 ModelScope 魔搭社区上的 4.1B 参数机器学习模型，采用 MIT 许可。

- **Repository**: michaelyuancb/ftp1_v0426_50kstep
- **License**: MIT
- **Parameters**: 4.1B
- **Downloads**: 1982
- **Stars**: 0
- **Last updated**: 2026-06-04

Source: https://www.modelscope.cn/models/michaelyuancb/ftp1_v0426_50kstep

---

# FTP-1 v0426 50kstep

`ftp1_pretrain_v0426_50kstep` is the 50k-step pretrained checkpoint of FTP-1, a general tactile policy for multimodal manipulation with vision, proprioception, language, and optional tactile input.

This checkpoint is mainly intended as a base model for downstream fine-tuning and research use.

FTP-1 is described in the main project materials as being pretrained on approximately 3,000 hours of heterogeneous tactile manipulation data.

## Notes

- Type: pretrained checkpoint
- Stage: v0426, 50k steps
- Inputs: image, state, language, optional tactile
- Output: action chunk prediction

## Links

- Project homepage: https://ftp1-policy.github.io/
- Open-source repository: https://github.com/michaelyuancb/ftp1-policy

---
license: MIT