# Fireworks AI 宣布其平台支持对 DeepSeek V4 Flash 0731 进行微调，提供 SFT、DPO 和 RL 训练能力，开发者可通过专用训练 API 使用

- 来源：Fireworks AI
- 发布时间：2026-08-06 04:33
- AIWatch 分数：61
- AIWatch 标记：未精选
- AIWatch 链接：https://aiwatch.icu/events/evt_01kz9vfjr0c1jzr9g93g3t3pzd
- 原文链接：https://x.com/FireworksAI_HQ/status/2085102033997287718

## 精选理由

常规快讯，保留列表

## AI 摘要

Fireworks AI 宣布其平台支持对 DeepSeek V4 Flash 0731 进行微调，提供 SFT、DPO 和 RL 训练能力，开发者可通过专用训练 API 使用。

## 正文

Training

Which base models you can train on Fireworks and the surfaces each one is available on.

Managed fine-tuning, the Training API, and serverless training all draw from the same base model catalog, but availability is decided per model: managed jobs by method (SFT, DPO, RFT), Training API jobs by parameter mode (LoRA or full-parameter).

Model availability

Pick a model to see the surfaces and methods it is enabled for, plus any training shapes that back it. Switch to All models for the full matrix.

Next steps