LLM
Phind CodeLlama 34B V1 is a fine-tuned version of the Code-Llama 34B LLM using an internal Phind dataset that achieved 67.6% pass@1 on HumanEval, beating GPT-4.
On-demand deployments allow you to use Phind CodeLlama 34B v1 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.
See the On-demand deployments guide for details.