Phind CodeLlama 34B Python V1 is a fine-tuned version of the CodeLlama 34B Python LLM using an internal Phind dataset that achieved 69.5% pass@1 on HumanEval, beating GPT-4.
Fine-tuningDocs | Phind CodeLlama 34B Python v1 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model |
On-demand DeploymentDocs | On-demand deployments allow you to use Phind CodeLlama 34B Python v1 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
