We beat GPT-4 on HumanEval with fine-tuned CodeLlama-34B!
Here's how we did it: phind.com/blog/code-llam…
🚀 Both models have been open-sourced on Huggingface: huggingface.co/Phind
Phind
105 posts
Phind
@phindsearch
AI answer engine for complex questions.
- Introducing Phind-405B, our new flagship model! Phind-405B scores 92% on HumanEval, matching Claude 3.5 Sonnet. We're particularly happy with its performance on real-world tasks, particularly when it comes to designing and implementing web apps. Our focus on technical topics
- Our GPT-4-beating coding model is now the default on Phind.com. It's also 5x faster than GPT-4. Learn more in our blog post: phind.com/blog/phind-mod…
- Introducing Phind-70B, our largest and most capable model to date! We think it offers the best overall user experience for developers amongst state-of-the-art models. phind.com/blog/introduci…
- 🚀 While ChatGPT is pausing signups, Phind continues to be better at programming while being 5x faster. We’ve been rapidly adding capacity and it’s only getting faster. Check it out ➡️ phind.com
- Phind has a new look! It's simpler, cleaner, and helps you focus on what matters. There's no easier way to get your technical questions answered than with Phind.
- GPT-4o is now available in Phind for all paid users! phind.com/plans
- Introducing our VS Code extension! Phind now knows when to search the web or your codebase -- no more tab switching.
- Announcing much faster Phind Model inference for Pro and Plus users. Your request will be served by a dedicated cluster powered by NVIDIA H100s for the lowest latency and a generation speed of up to 100 tokens per second. If you’re not yet a Pro user, join us at
- With Hello, get an answers and code snippets instantly using AI. To any question. Hover over the answer to see cited sources. And, it's not built on top of GPT -- we use our own proprietary models. sayhello.so
00:00 - 🚀 Introducing GPT-4 with 32K context for Phind Pro users. If you’re not yet a subscriber, join us at phind.com/plans.
