68 repos across 3 sub-areas
Large language models fine-tuned and optimized for code generation tasks, along with infrastructure for deploying and serving text-generation models at scale. The cluster centers on specialized code LLMs (Wizardcoder, Speechless variants, and similar models) designed to improve upon base models like CodeLlama through instruction-tuning and alignment techniques. Repositories here cover model weights, inference servers, and deployment patterns compatible with standard text-generation endpoints.
Cluster 462317
32 repos
Cluster 462318
20 repos
Large Language Model Fine-tuning and Inference
16 repos
Text generation models and frameworks for deploying, fine-tuning, and optimizing large language models (LLMs), particularly Mistral-based variants. The cluster centers on transformer-based models packaged with safetensors, model indices, and text-generation-inference infrastructure. Repositories here span model checkpoints, GGUF quantizations, and tooling for efficient inference and adaptation of open-source LLMs.