Model Releases
The team @tryheidi didn't want to keep renting someone else's intelligence. So Heidi fine-tuned an open model that beat Gemini Pro on qualit…
The team @tryheidi didn't want to keep renting someone else's intelligence. So Heidi fine-tuned an open model that beat Gemini Pro on quality in their internal evals, and ran with 3.5x faster latency
The team @tryheidi didn't want to keep renting someone else's intelligence. So Heidi fine-tuned an open model that beat Gemini Pro on quality in their internal evals, and ran with 3.5x faster latency (25s → 7s). From POC to production in 4 weeks. Get the full scoop → https://fireworks.ai/blog/Heidi-Health
Related
- Weekends are for vibe coding. But are your vibes continuously improving? Fine-tune your own model → stop waiting on someone else's release c…
- Fine-tuning on your proprietary data is the highest leverage thing you can do. Prompts get copied overnight. A model trained on your data, y…
- Another proof point for the open-weights thesis. From @RampLabs: 'If we built this again, we'd lean more on open-weight models.' Ramp pointe…
Source: Fireworks AI (X) | 2026-07-21