Together launches Post-Training service: turn open models into custom models via SFT or RL
togethercompute · x · 2026-10-20
Together has launched Together Post-Training, a service that turns open models into custom models you own using SFT or RL.
- Users define their own data, rewards, environments and training loop; Together runs the tuned infrastructure underneath
- Every model gets a pre-tested GPU setup with rollout engines tuned for RL (training engine, inference engines, kernels, precision)
- Training and generation are kept in sync, so quality observed in training holds up in serving
- Start from cookbook recipes or have a coding agent write the script; train LoRA adapters or full weights, running multiple experiments on the same GPUs
Related event: Together Launches Post-Training Service for Custom Models via SFT and RL(3 posts)→
More from coding & agent
- Perplexity's Open-Source Sandbox Platform SPACE Joins Crusoe Cloud's Managed AI Portfolio — AravSrinivas · 2026-10-20
- SpudStack uses Grok to review agent plans with PASS/FAIL verdicts — agents can't sign off their own work — alexcovo_eth · 2026-10-20
- Cloudflare MCP Server adds step-up auth: agents request scopes on demand — irvinebroque · 2026-10-20
- Skill Harbor, a skill directory for Muse agents, opens with a 10-member ecosystem — InformationOk4877 · 2026-10-20
- Nine conditions for AI to actually show up positive in your P&L — vasuman · 2026-10-20
- Three probes track post-training SWE-bench rankings, BPB hits ρ=0.964 — hyunw_kim · 2026-10-20